Upload continuous evaluation checkpoints, batch 36

continuous/smollm2/mc2_g14_224/finetune/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d370f3f37d6a04bd98ebd7222072b206a20c6df894434b2189ba2abd9b834468
+size 2357886088

continuous/smollm2/mc2_g14_224/finetune/model.safetensors.index.json

@@ -0,0 +1,815 @@
+{
+  "metadata": {
+    "total_parameters": 3563889920,
+    "total_size": 7344318976
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.class_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.positional_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.proj": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

continuous/smollm2/mc2_g14_224/finetune/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

continuous/smollm2/mc2_g14_224/finetune/tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_g14_224/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850596842510589,
+      "grad_norm": 3.1622438430786133,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 1.2884,
+      "step": 10
+    },
+    {
+      "epoch": 0.007701193685021178,
+      "grad_norm": 2.095348358154297,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.1338,
+      "step": 20
+    },
+    {
+      "epoch": 0.011551790527531768,
+      "grad_norm": 1.9559576511383057,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.0115,
+      "step": 30
+    },
+    {
+      "epoch": 0.015402387370042356,
+      "grad_norm": 1.3467422723770142,
+      "learning_rate": 5e-06,
+      "loss": 0.9603,
+      "step": 40
+    },
+    {
+      "epoch": 0.019252984212552945,
+      "grad_norm": 1.2901713848114014,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 0.9458,
+      "step": 50
+    },
+    {
+      "epoch": 0.023103581055063535,
+      "grad_norm": 0.2695236802101135,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.8722,
+      "step": 60
+    },
+    {
+      "epoch": 0.026954177897574125,
+      "grad_norm": 0.22157791256904602,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.8277,
+      "step": 70
+    },
+    {
+      "epoch": 0.030804774740084712,
+      "grad_norm": 0.22338208556175232,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.8406,
+      "step": 80
+    },
+    {
+      "epoch": 0.0346553715825953,
+      "grad_norm": 0.22944317758083344,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.8255,
+      "step": 90
+    },
+    {
+      "epoch": 0.03850596842510589,
+      "grad_norm": 0.1857936978340149,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.7932,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235656526761648,
+      "grad_norm": 0.20593543350696564,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.7844,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620716211012707,
+      "grad_norm": 0.20112857222557068,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8035,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005775895263766,
+      "grad_norm": 0.19560588896274567,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.7786,
+      "step": 130
+    },
+    {
+      "epoch": 0.05390835579514825,
+      "grad_norm": 0.20608371496200562,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.7927,
+      "step": 140
+    },
+    {
+      "epoch": 0.05775895263765884,
+      "grad_norm": 0.2172311395406723,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.7699,
+      "step": 150
+    },
+    {
+      "epoch": 0.061609549480169425,
+      "grad_norm": 0.18276295065879822,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.7755,
+      "step": 160
+    },
+    {
+      "epoch": 0.06546014632268002,
+      "grad_norm": 0.1757490634918213,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.7764,
+      "step": 170
+    },
+    {
+      "epoch": 0.0693107431651906,
+      "grad_norm": 0.18769043684005737,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.8078,
+      "step": 180
+    },
+    {
+      "epoch": 0.07316134000770119,
+      "grad_norm": 0.2065918892621994,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.7947,
+      "step": 190
+    },
+    {
+      "epoch": 0.07701193685021178,
+      "grad_norm": 0.1856461465358734,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.7931,
+      "step": 200
+    },
+    {
+      "epoch": 0.08086253369272237,
+      "grad_norm": 0.19743920862674713,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.781,
+      "step": 210
+    },
+    {
+      "epoch": 0.08471313053523297,
+      "grad_norm": 0.18190714716911316,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.77,
+      "step": 220
+    },
+    {
+      "epoch": 0.08856372737774355,
+      "grad_norm": 0.18760724365711212,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.7667,
+      "step": 230
+    },
+    {
+      "epoch": 0.09241432422025414,
+      "grad_norm": 0.194053515791893,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.7611,
+      "step": 240
+    },
+    {
+      "epoch": 0.09626492106276473,
+      "grad_norm": 0.19743536412715912,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.7791,
+      "step": 250
+    },
+    {
+      "epoch": 0.10011551790527531,
+      "grad_norm": 0.17157597839832306,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.7755,
+      "step": 260
+    },
+    {
+      "epoch": 0.1039661147477859,
+      "grad_norm": 0.18482477962970734,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.7583,
+      "step": 270
+    },
+    {
+      "epoch": 0.1078167115902965,
+      "grad_norm": 0.1717097908258438,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.7558,
+      "step": 280
+    },
+    {
+      "epoch": 0.11166730843280709,
+      "grad_norm": 0.17732089757919312,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.7876,
+      "step": 290
+    },
+    {
+      "epoch": 0.11551790527531768,
+      "grad_norm": 0.16475197672843933,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.7458,
+      "step": 300
+    },
+    {
+      "epoch": 0.11936850211782826,
+      "grad_norm": 0.16797596216201782,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.7515,
+      "step": 310
+    },
+    {
+      "epoch": 0.12321909896033885,
+      "grad_norm": 0.18339043855667114,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.7604,
+      "step": 320
+    },
+    {
+      "epoch": 0.12706969580284944,
+      "grad_norm": 0.18005502223968506,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.13092029264536004,
+      "grad_norm": 0.17473933100700378,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.7659,
+      "step": 340
+    },
+    {
+      "epoch": 0.1347708894878706,
+      "grad_norm": 0.18880513310432434,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.7703,
+      "step": 350
+    },
+    {
+      "epoch": 0.1386214863303812,
+      "grad_norm": 0.1780232936143875,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.7518,
+      "step": 360
+    },
+    {
+      "epoch": 0.1424720831728918,
+      "grad_norm": 0.19660069048404694,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.7795,
+      "step": 370
+    },
+    {
+      "epoch": 0.14632268001540238,
+      "grad_norm": 0.17364242672920227,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.745,
+      "step": 380
+    },
+    {
+      "epoch": 0.15017327685791299,
+      "grad_norm": 0.1848473697900772,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.7474,
+      "step": 390
+    },
+    {
+      "epoch": 0.15402387370042356,
+      "grad_norm": 0.1595541387796402,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.7545,
+      "step": 400
+    },
+    {
+      "epoch": 0.15787447054293416,
+      "grad_norm": 0.18609967827796936,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.7511,
+      "step": 410
+    },
+    {
+      "epoch": 0.16172506738544473,
+      "grad_norm": 0.17785204946994781,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.7658,
+      "step": 420
+    },
+    {
+      "epoch": 0.16557566422795533,
+      "grad_norm": 0.17662639915943146,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.7475,
+      "step": 430
+    },
+    {
+      "epoch": 0.16942626107046593,
+      "grad_norm": 0.1697656512260437,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.7538,
+      "step": 440
+    },
+    {
+      "epoch": 0.1732768579129765,
+      "grad_norm": 0.17753742635250092,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7395,
+      "step": 450
+    },
+    {
+      "epoch": 0.1771274547554871,
+      "grad_norm": 0.18957072496414185,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.7488,
+      "step": 460
+    },
+    {
+      "epoch": 0.18097805159799768,
+      "grad_norm": 0.1630454957485199,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.7511,
+      "step": 470
+    },
+    {
+      "epoch": 0.18482864844050828,
+      "grad_norm": 0.18532635271549225,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.7497,
+      "step": 480
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 0.16529159247875214,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.7439,
+      "step": 490
+    },
+    {
+      "epoch": 0.19252984212552945,
+      "grad_norm": 0.15975125133991241,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.7476,
+      "step": 500
+    },
+    {
+      "epoch": 0.19638043896804006,
+      "grad_norm": 0.17618444561958313,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7372,
+      "step": 510
+    },
+    {
+      "epoch": 0.20023103581055063,
+      "grad_norm": 0.1799439936876297,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.7608,
+      "step": 520
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.17784644663333893,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.744,
+      "step": 530
+    },
+    {
+      "epoch": 0.2079322294955718,
+      "grad_norm": 0.17866221070289612,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.7543,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117828263380824,
+      "grad_norm": 0.1793346107006073,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.7593,
+      "step": 550
+    },
+    {
+      "epoch": 0.215633423180593,
+      "grad_norm": 0.16475343704223633,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.7618,
+      "step": 560
+    },
+    {
+      "epoch": 0.21948402002310358,
+      "grad_norm": 0.18559783697128296,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.775,
+      "step": 570
+    },
+    {
+      "epoch": 0.22333461686561418,
+      "grad_norm": 0.1836942881345749,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.7437,
+      "step": 580
+    },
+    {
+      "epoch": 0.22718521370812475,
+      "grad_norm": 0.16508834064006805,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.758,
+      "step": 590
+    },
+    {
+      "epoch": 0.23103581055063535,
+      "grad_norm": 0.15858276188373566,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.7545,
+      "step": 600
+    },
+    {
+      "epoch": 0.23488640739314592,
+      "grad_norm": 0.1873605102300644,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.7737,
+      "step": 610
+    },
+    {
+      "epoch": 0.23873700423565652,
+      "grad_norm": 0.1651591658592224,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.7525,
+      "step": 620
+    },
+    {
+      "epoch": 0.24258760107816713,
+      "grad_norm": 0.1724609136581421,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.2464381979206777,
+      "grad_norm": 0.184341162443161,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.7623,
+      "step": 640
+    },
+    {
+      "epoch": 0.25028879476318827,
+      "grad_norm": 0.16441811621189117,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7239,
+      "step": 650
+    },
+    {
+      "epoch": 0.25413939160569887,
+      "grad_norm": 0.17331954836845398,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.7487,
+      "step": 660
+    },
+    {
+      "epoch": 0.2579899884482095,
+      "grad_norm": 0.18033401668071747,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.7578,
+      "step": 670
+    },
+    {
+      "epoch": 0.2618405852907201,
+      "grad_norm": 0.1618831604719162,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7399,
+      "step": 680
+    },
+    {
+      "epoch": 0.2656911821332307,
+      "grad_norm": 0.1646553874015808,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.7488,
+      "step": 690
+    },
+    {
+      "epoch": 0.2695417789757412,
+      "grad_norm": 0.1714385449886322,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.7613,
+      "step": 700
+    },
+    {
+      "epoch": 0.2733923758182518,
+      "grad_norm": 0.15989945828914642,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7434,
+      "step": 710
+    },
+    {
+      "epoch": 0.2772429726607624,
+      "grad_norm": 0.162005215883255,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7434,
+      "step": 720
+    },
+    {
+      "epoch": 0.281093569503273,
+      "grad_norm": 0.16881293058395386,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.7527,
+      "step": 730
+    },
+    {
+      "epoch": 0.2849441663457836,
+      "grad_norm": 0.16939964890480042,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7379,
+      "step": 740
+    },
+    {
+      "epoch": 0.28879476318829417,
+      "grad_norm": 0.15472887456417084,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7361,
+      "step": 750
+    },
+    {
+      "epoch": 0.29264536003080477,
+      "grad_norm": 0.16578936576843262,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7329,
+      "step": 760
+    },
+    {
+      "epoch": 0.29649595687331537,
+      "grad_norm": 0.14813192188739777,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.7503,
+      "step": 770
+    },
+    {
+      "epoch": 0.30034655371582597,
+      "grad_norm": 0.18033084273338318,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.7466,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041971505583365,
+      "grad_norm": 0.16499286890029907,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7292,
+      "step": 790
+    },
+    {
+      "epoch": 0.3080477474008471,
+      "grad_norm": 0.1678442358970642,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.7509,
+      "step": 800
+    },
+    {
+      "epoch": 0.3118983442433577,
+      "grad_norm": 0.16410832107067108,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7494,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157489410858683,
+      "grad_norm": 0.16838516294956207,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.7456,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195995379283789,
+      "grad_norm": 0.16842912137508392,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.7332,
+      "step": 830
+    },
+    {
+      "epoch": 0.32345013477088946,
+      "grad_norm": 0.16925445199012756,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.7333,
+      "step": 840
+    },
+    {
+      "epoch": 0.32730073161340006,
+      "grad_norm": 0.16095510125160217,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.7426,
+      "step": 850
+    },
+    {
+      "epoch": 0.33115132845591067,
+      "grad_norm": 0.1695629507303238,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7349,
+      "step": 860
+    },
+    {
+      "epoch": 0.33500192529842127,
+      "grad_norm": 0.1557825654745102,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7371,
+      "step": 870
+    },
+    {
+      "epoch": 0.33885252214093187,
+      "grad_norm": 0.16713857650756836,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.7417,
+      "step": 880
+    },
+    {
+      "epoch": 0.3427031189834424,
+      "grad_norm": 0.17240813374519348,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7345,
+      "step": 890
+    },
+    {
+      "epoch": 0.346553715825953,
+      "grad_norm": 0.15577691793441772,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.7349,
+      "step": 900
+    },
+    {
+      "epoch": 0.3504043126684636,
+      "grad_norm": 0.18714292347431183,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.7271,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542549095109742,
+      "grad_norm": 0.1654650717973709,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7345,
+      "step": 920
+    },
+    {
+      "epoch": 0.3581055063534848,
+      "grad_norm": 0.19921469688415527,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7158,
+      "step": 930
+    },
+    {
+      "epoch": 0.36195610319599536,
+      "grad_norm": 0.16582702100276947,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.7475,
+      "step": 940
+    },
+    {
+      "epoch": 0.36580670003850596,
+      "grad_norm": 0.17667463421821594,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.7627,
+      "step": 950
+    },
+    {
+      "epoch": 0.36965729688101656,
+      "grad_norm": 0.1690313071012497,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7573,
+      "step": 960
+    },
+    {
+      "epoch": 0.37350789372352716,
+      "grad_norm": 0.15988481044769287,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7272,
+      "step": 970
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.16571684181690216,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7365,
+      "step": 980
+    },
+    {
+      "epoch": 0.3812090874085483,
+      "grad_norm": 0.17036551237106323,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7232,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850596842510589,
+      "grad_norm": 0.16631658375263214,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.7349,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3889102810935695,
+      "grad_norm": 0.15797334909439087,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.7555,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3927608779360801,
+      "grad_norm": 0.1806025356054306,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.7526,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39661147477859066,
+      "grad_norm": 0.1508234590291977,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7486,
+      "step": 1030
+    },
+    {
+      "epoch": 0.40046207162110126,
+      "grad_norm": 0.1736387014389038,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.7374,
+      "step": 1040
+    },
+    {
+      "epoch": 0.40431266846361186,
+      "grad_norm": 0.15402837097644806,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.7312,
+      "step": 1050
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.1566491425037384,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.738,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41201386214863306,
+      "grad_norm": 0.16736960411071777,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.73,
+      "step": 1070
+    },
+    {
+      "epoch": 0.4158644589911436,
+      "grad_norm": 0.15196648240089417,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.7553,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4197150558336542,
+      "grad_norm": 0.1790315955877304,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7379,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235656526761648,
+      "grad_norm": 0.16407856345176697,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.7501,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4274162495186754,
+      "grad_norm": 0.1690288782119751,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.741,
+      "step": 1110
+    },
+    {
+      "epoch": 0.431266846361186,
+      "grad_norm": 0.17213088274002075,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7399,
+      "step": 1120
+    },
+    {
+      "epoch": 0.43511744320369655,
+      "grad_norm": 0.17390041053295135,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7207,
+      "step": 1130
+    },
+    {
+      "epoch": 0.43896804004620715,
+      "grad_norm": 0.18004390597343445,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7441,
+      "step": 1140
+    },
+    {
+      "epoch": 0.44281863688871775,
+      "grad_norm": 0.1707184612751007,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7283,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44666923373122835,
+      "grad_norm": 0.1940920501947403,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.7575,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45051983057373896,
+      "grad_norm": 0.15715067088603973,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.7647,
+      "step": 1170
+    },
+    {
+      "epoch": 0.4543704274162495,
+      "grad_norm": 0.1666465401649475,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7458,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4582210242587601,
+      "grad_norm": 0.15321527421474457,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7215,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4620716211012707,
+      "grad_norm": 0.16777202486991882,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7304,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4659222179437813,
+      "grad_norm": 0.16640929877758026,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.7284,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46977281478629185,
+      "grad_norm": 0.16483311355113983,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7534,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47362341162880245,
+      "grad_norm": 0.16042590141296387,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7503,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47747400847131305,
+      "grad_norm": 0.1577351689338684,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.728,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48132460531382365,
+      "grad_norm": 0.1595667451620102,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7212,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48517520215633425,
+      "grad_norm": 0.17429611086845398,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7345,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4890257989988448,
+      "grad_norm": 0.1780616194009781,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7104,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928763958413554,
+      "grad_norm": 0.1733609288930893,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7294,
+      "step": 1280
+    },
+    {
+      "epoch": 0.496726992683866,
+      "grad_norm": 0.15647843480110168,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.7399,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005775895263765,
+      "grad_norm": 0.1658322662115097,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5044281863688872,
+      "grad_norm": 0.17129601538181305,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.7508,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082787832113977,
+      "grad_norm": 0.17405052483081818,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7204,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5121293800539084,
+      "grad_norm": 0.17743641138076782,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.729,
+      "step": 1330
+    },
+    {
+      "epoch": 0.515979976896419,
+      "grad_norm": 0.16059216856956482,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7334,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5198305737389295,
+      "grad_norm": 0.16153599321842194,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7312,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236811705814401,
+      "grad_norm": 0.1808532476425171,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.7474,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5275317674239507,
+      "grad_norm": 0.1683477759361267,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.739,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313823642664613,
+      "grad_norm": 0.16155141592025757,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.753,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5352329611089719,
+      "grad_norm": 0.17086820304393768,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7282,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390835579514824,
+      "grad_norm": 0.16252751648426056,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7289,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5429341547939931,
+      "grad_norm": 0.17524836957454681,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7476,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467847516365036,
+      "grad_norm": 0.17716297507286072,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7303,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5506353484790143,
+      "grad_norm": 0.17218923568725586,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.7444,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544859453215248,
+      "grad_norm": 0.17851218581199646,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7446,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5583365421640354,
+      "grad_norm": 0.1706838458776474,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.729,
+      "step": 1450
+    },
+    {
+      "epoch": 0.562187139006546,
+      "grad_norm": 0.16858817636966705,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7339,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 0.16259799897670746,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7287,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698883326915672,
+      "grad_norm": 0.1691897213459015,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7233,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5737389295340778,
+      "grad_norm": 0.16453805565834045,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7317,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775895263765883,
+      "grad_norm": 0.1681760996580124,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.7427,
+      "step": 1500
+    },
+    {
+      "epoch": 0.581440123219099,
+      "grad_norm": 0.1683240681886673,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7362,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852907200616095,
+      "grad_norm": 0.16526831686496735,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.7437,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5891413169041202,
+      "grad_norm": 0.15572451055049896,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.7442,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929919137466307,
+      "grad_norm": 0.16924837231636047,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.7456,
+      "step": 1540
+    },
+    {
+      "epoch": 0.5968425105891413,
+      "grad_norm": 0.1614847034215927,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.7343,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006931074316519,
+      "grad_norm": 0.15508674085140228,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7451,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6045437042741625,
+      "grad_norm": 0.17822398245334625,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.7505,
+      "step": 1570
+    },
+    {
+      "epoch": 0.608394301116673,
+      "grad_norm": 0.17663618922233582,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.7426,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.14470122754573822,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.738,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160954948016942,
+      "grad_norm": 0.16043484210968018,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7339,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6199460916442049,
+      "grad_norm": 0.15655358135700226,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7122,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6237966884867154,
+      "grad_norm": 0.16765274107456207,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7126,
+      "step": 1620
+    },
+    {
+      "epoch": 0.627647285329226,
+      "grad_norm": 0.16464398801326752,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7383,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314978821717366,
+      "grad_norm": 0.15585027635097504,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7301,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6353484790142472,
+      "grad_norm": 0.16600026190280914,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7442,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391990758567578,
+      "grad_norm": 0.16264180839061737,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7211,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6430496726992684,
+      "grad_norm": 0.1860174685716629,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.738,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6469002695417789,
+      "grad_norm": 0.16757120192050934,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7314,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6507508663842896,
+      "grad_norm": 0.1717720776796341,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7251,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6546014632268001,
+      "grad_norm": 0.15982608497142792,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7292,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6584520600693108,
+      "grad_norm": 0.1717679351568222,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7338,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6623026569118213,
+      "grad_norm": 0.18018200993537903,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7267,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6661532537543319,
+      "grad_norm": 0.1777120977640152,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.7337,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6700038505968425,
+      "grad_norm": 0.16606228053569794,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7407,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6738544474393531,
+      "grad_norm": 0.1572098582983017,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7351,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6777050442818637,
+      "grad_norm": 0.1584535539150238,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7269,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6815556411243743,
+      "grad_norm": 0.1755974292755127,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.7629,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6854062379668848,
+      "grad_norm": 0.16607578098773956,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7393,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6892568348093955,
+      "grad_norm": 0.17227479815483093,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.7551,
+      "step": 1790
+    },
+    {
+      "epoch": 0.693107431651906,
+      "grad_norm": 0.159317746758461,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7242,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6969580284944167,
+      "grad_norm": 0.16478827595710754,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7171,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7008086253369272,
+      "grad_norm": 0.15710191428661346,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.7405,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7046592221794378,
+      "grad_norm": 0.1616377830505371,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7233,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7085098190219484,
+      "grad_norm": 0.16392791271209717,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7302,
+      "step": 1840
+    },
+    {
+      "epoch": 0.712360415864459,
+      "grad_norm": 0.16595213115215302,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.7438,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7162110127069696,
+      "grad_norm": 0.16082945466041565,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7408,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7200616095494802,
+      "grad_norm": 0.16564622521400452,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7325,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7239122063919907,
+      "grad_norm": 0.16170759499073029,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7423,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7277628032345014,
+      "grad_norm": 0.16761024296283722,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7284,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7316134000770119,
+      "grad_norm": 0.1736161708831787,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7387,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7354639969195226,
+      "grad_norm": 0.15771009027957916,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7353,
+      "step": 1910
+    },
+    {
+      "epoch": 0.7393145937620331,
+      "grad_norm": 0.16274334490299225,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.7257,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7431651906045437,
+      "grad_norm": 0.17500782012939453,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7436,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7470157874470543,
+      "grad_norm": 0.15915387868881226,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.7427,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7508663842895649,
+      "grad_norm": 0.16269752383232117,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7271,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.18475228548049927,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7506,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7585675779745861,
+      "grad_norm": 0.17280326783657074,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7412,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7624181748170966,
+      "grad_norm": 0.17638637125492096,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7415,
+      "step": 1980
+    },
+    {
+      "epoch": 0.7662687716596073,
+      "grad_norm": 0.17892619967460632,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.7299,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7701193685021178,
+      "grad_norm": 0.16374772787094116,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7306,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7739699653446284,
+      "grad_norm": 0.1570831686258316,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7376,
+      "step": 2010
+    },
+    {
+      "epoch": 0.777820562187139,
+      "grad_norm": 0.15511859953403473,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.718,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7816711590296496,
+      "grad_norm": 0.16592757403850555,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7134,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7855217558721602,
+      "grad_norm": 0.1634754091501236,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7285,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7893723527146708,
+      "grad_norm": 0.15767942368984222,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7314,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7932229495571813,
+      "grad_norm": 0.14939111471176147,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7162,
+      "step": 2060
+    },
+    {
+      "epoch": 0.797073546399692,
+      "grad_norm": 0.16796280443668365,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.732,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8009241432422025,
+      "grad_norm": 0.1567056030035019,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7088,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8047747400847132,
+      "grad_norm": 0.15788625180721283,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7363,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8086253369272237,
+      "grad_norm": 0.15417617559432983,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.7271,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8124759337697343,
+      "grad_norm": 0.16111932694911957,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7313,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.1769952028989792,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7473,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8201771274547555,
+      "grad_norm": 0.16215193271636963,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7278,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8240277242972661,
+      "grad_norm": 0.16830527782440186,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7297,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8278783211397767,
+      "grad_norm": 0.15804657340049744,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7191,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8317289179822872,
+      "grad_norm": 0.15747228264808655,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7398,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8355795148247979,
+      "grad_norm": 0.1686367243528366,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7334,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8394301116673084,
+      "grad_norm": 0.1599309891462326,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7302,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8432807085098191,
+      "grad_norm": 0.16978369653224945,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.7288,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8471313053523296,
+      "grad_norm": 0.17487354576587677,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7314,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8509819021948402,
+      "grad_norm": 0.15299537777900696,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7036,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8548324990373508,
+      "grad_norm": 0.15450167655944824,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.736,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586830958798614,
+      "grad_norm": 0.1759854108095169,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7294,
+      "step": 2230
+    },
+    {
+      "epoch": 0.862533692722372,
+      "grad_norm": 0.15966801345348358,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.742,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663842895648826,
+      "grad_norm": 0.1647414267063141,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7293,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8702348864073931,
+      "grad_norm": 0.19251467287540436,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7125,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740854832499038,
+      "grad_norm": 0.15758617222309113,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7294,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8779360800924143,
+      "grad_norm": 0.15684367716312408,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7366,
+      "step": 2280
+    },
+    {
+      "epoch": 0.881786676934925,
+      "grad_norm": 0.1575993001461029,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.737,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8856372737774355,
+      "grad_norm": 0.1648300290107727,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.7194,
+      "step": 2300
+    },
+    {
+      "epoch": 0.889487870619946,
+      "grad_norm": 0.15544557571411133,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7312,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8933384674624567,
+      "grad_norm": 0.1553572714328766,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7333,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971890643049673,
+      "grad_norm": 0.1685064435005188,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7429,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9010396611474779,
+      "grad_norm": 0.15903566777706146,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7347,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048902579899885,
+      "grad_norm": 0.16196703910827637,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7153,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908740854832499,
+      "grad_norm": 0.16023315489292145,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7303,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125914516750097,
+      "grad_norm": 0.1769438087940216,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7233,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9164420485175202,
+      "grad_norm": 0.15825696289539337,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7348,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202926453600309,
+      "grad_norm": 0.16054482758045197,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7466,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9241432422025414,
+      "grad_norm": 0.1774730682373047,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7393,
+      "step": 2400
+    },
+    {
+      "epoch": 0.927993839045052,
+      "grad_norm": 0.16319742798805237,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7188,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9318444358875626,
+      "grad_norm": 0.1570887714624405,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7477,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9356950327300732,
+      "grad_norm": 0.1639893501996994,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.7412,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9395456295725837,
+      "grad_norm": 0.16070027649402618,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7295,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 0.1713898777961731,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.719,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9472468232576049,
+      "grad_norm": 0.17353764176368713,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7447,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510974201001156,
+      "grad_norm": 0.1690940409898758,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7409,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9549480169426261,
+      "grad_norm": 0.1628992110490799,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7268,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587986137851366,
+      "grad_norm": 0.15716297924518585,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7292,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9626492106276473,
+      "grad_norm": 0.16145417094230652,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7307,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664998074701578,
+      "grad_norm": 0.15447816252708435,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.73,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9703504043126685,
+      "grad_norm": 0.1641196757555008,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7438,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974201001155179,
+      "grad_norm": 0.16590984165668488,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7239,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9780515979976896,
+      "grad_norm": 0.15721890330314636,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7257,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9819021948402002,
+      "grad_norm": 0.15160682797431946,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7396,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9857527916827108,
+      "grad_norm": 0.15466949343681335,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.7253,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9896033885252215,
+      "grad_norm": 0.16083106398582458,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7216,
+      "step": 2570
+    },
+    {
+      "epoch": 0.993453985367732,
+      "grad_norm": 0.1579686403274536,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7127,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9973045822102425,
+      "grad_norm": 0.17146477103233337,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7454,
+      "step": 2590
+    },
+    {
+      "epoch": 1.0,
+      "step": 2597,
+      "total_flos": 1.2141735976569405e+19,
+      "train_loss": 0.7493066128557078,
+      "train_runtime": 15521.965,
+      "train_samples_per_second": 42.836,
+      "train_steps_per_second": 0.167
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 584317136,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2141735976569405e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/smollm2/mc2_g14_224/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac5c94e8aa40198b4b8ba43392dbeab975283773f0f7c49f8e2b4044e3028ac
+size 6264

continuous/smollm2/mc2_g14_224/pretrain/config.json

@@ -0,0 +1,70 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_hidden_size": 1664,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-bigG-14-worldwide",
+  "mm_vision_tower_lr": null,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_g14_224.pt",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_g14_224/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c6d57ae87dd539e67890e3efc0b975132f30abe6324ee02be4f5d7b40ce53e
+size 30427192

continuous/smollm2/mc2_g14_224/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 1.0039424896240234,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 3.8846,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.17363029718399048,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 2.9507,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.0591820627450943,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 2.8215,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.11193465441465378,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 2.7583,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.14545811712741852,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 2.7407,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.08581174165010452,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 2.7024,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.08783824741840363,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 2.66,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.19248084723949432,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 2.6089,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.1298256516456604,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 2.5616,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.13502322137355804,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 2.5184,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.1526024341583252,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 2.4674,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.1638764888048172,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 2.4387,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.15917429327964783,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 2.3976,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.12591172754764557,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 2.3728,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.14404301345348358,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 2.3633,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.11663815379142761,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 2.3371,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.1295832246541977,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 2.3263,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.1714584231376648,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 2.308,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.144470676779747,
+      "learning_rate": 0.000779204504653894,
+      "loss": 2.2976,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.13648849725723267,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 2.2688,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.15922284126281738,
+      "learning_rate": 0.00072685988254984,
+      "loss": 2.2625,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.11901236325502396,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 2.2655,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.13847114145755768,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 2.2538,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.15086793899536133,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 2.2435,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.1341017335653305,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 2.2382,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.11809761077165604,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 2.2397,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.1329304426908493,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 2.215,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.11744008213281631,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 2.2172,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.11246025562286377,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 2.2008,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.11394795030355453,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 2.1991,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.18558502197265625,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 2.2017,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.1243106946349144,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 2.1994,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.13286319375038147,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 2.1815,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.12835507094860077,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 2.1823,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.13167358934879303,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 2.1789,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.14037467539310455,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 2.1798,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.1329239159822464,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 2.1705,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.11213938891887665,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 2.1746,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.11000218242406845,
+      "learning_rate": 0.000208323983828828,
+      "loss": 2.1603,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.11713051050901413,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 2.1594,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.12175421416759491,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 2.1567,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.12579183280467987,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 2.1494,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.1102660596370697,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 2.1488,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.123475581407547,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 2.158,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.11208569258451462,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 2.15,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.11094208061695099,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 2.1405,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.10838998854160309,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 2.136,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.10880545526742935,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 2.1375,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.10273294150829315,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 2.1457,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.10973713546991348,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 2.147,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.10031898319721222,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 2.1384,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.10313807427883148,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 2.1354,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.10801209509372711,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 2.1381,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.11000273376703262,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 2.1383,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 7.201747082925834e+17,
+      "train_loss": 2.3306150856368038,
+      "train_runtime": 1937.0166,
+      "train_samples_per_second": 288.138,
+      "train_steps_per_second": 0.281
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 34658176,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.201747082925834e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/smollm2/mc2_g14_378/finetune/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

continuous/smollm2/mc2_g14_378/finetune/config.json

@@ -0,0 +1,70 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_hidden_size": 1664,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-bigG-14-worldwide-378",
+  "mm_vision_tower_lr": null,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_g14_378.pt",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_g14_378/finetune/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.57.6"
+}

continuous/smollm2/mc2_g14_378/finetune/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca38eb94c1b93626213fb09bb3c2a9e5346f937fbe90f5c1230494db0d24c34
+size 4988118096

continuous/smollm2/mc2_g14_378/finetune/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffff7682a6efe7d7df0b4bb26c2d39f27d7f153047d0f1fda0b77633a9ba7690
+size 2357886088

continuous/smollm2/mc2_g14_378/finetune/model.safetensors.index.json

@@ -0,0 +1,815 @@
+{
+  "metadata": {
+    "total_parameters": 3564676992,
+    "total_size": 7345893120
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.class_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.positional_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.proj": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

continuous/smollm2/mc2_g14_378/finetune/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

continuous/smollm2/mc2_g14_378/finetune/tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_g14_378/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850596842510589,
+      "grad_norm": 3.0431768894195557,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 1.2429,
+      "step": 10
+    },
+    {
+      "epoch": 0.007701193685021178,
+      "grad_norm": 2.0823428630828857,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.0823,
+      "step": 20
+    },
+    {
+      "epoch": 0.011551790527531768,
+      "grad_norm": 1.9934183359146118,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 0.9731,
+      "step": 30
+    },
+    {
+      "epoch": 0.015402387370042356,
+      "grad_norm": 1.346245527267456,
+      "learning_rate": 5e-06,
+      "loss": 0.9266,
+      "step": 40
+    },
+    {
+      "epoch": 0.019252984212552945,
+      "grad_norm": 1.2828943729400635,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 0.9137,
+      "step": 50
+    },
+    {
+      "epoch": 0.023103581055063535,
+      "grad_norm": 0.25736886262893677,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.8412,
+      "step": 60
+    },
+    {
+      "epoch": 0.026954177897574125,
+      "grad_norm": 0.218653604388237,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.7963,
+      "step": 70
+    },
+    {
+      "epoch": 0.030804774740084712,
+      "grad_norm": 0.22179266810417175,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.8104,
+      "step": 80
+    },
+    {
+      "epoch": 0.0346553715825953,
+      "grad_norm": 0.20089474320411682,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.7946,
+      "step": 90
+    },
+    {
+      "epoch": 0.03850596842510589,
+      "grad_norm": 0.20093664526939392,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.7609,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235656526761648,
+      "grad_norm": 0.1889592558145523,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.7557,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620716211012707,
+      "grad_norm": 0.216338649392128,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.7739,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005775895263766,
+      "grad_norm": 0.1979912519454956,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.7489,
+      "step": 130
+    },
+    {
+      "epoch": 0.05390835579514825,
+      "grad_norm": 0.21476469933986664,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.7654,
+      "step": 140
+    },
+    {
+      "epoch": 0.05775895263765884,
+      "grad_norm": 0.21097643673419952,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.7407,
+      "step": 150
+    },
+    {
+      "epoch": 0.061609549480169425,
+      "grad_norm": 0.19116058945655823,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.748,
+      "step": 160
+    },
+    {
+      "epoch": 0.06546014632268002,
+      "grad_norm": 0.1733359694480896,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.7502,
+      "step": 170
+    },
+    {
+      "epoch": 0.0693107431651906,
+      "grad_norm": 0.19053015112876892,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.779,
+      "step": 180
+    },
+    {
+      "epoch": 0.07316134000770119,
+      "grad_norm": 0.21045449376106262,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.7658,
+      "step": 190
+    },
+    {
+      "epoch": 0.07701193685021178,
+      "grad_norm": 0.1917572021484375,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.7641,
+      "step": 200
+    },
+    {
+      "epoch": 0.08086253369272237,
+      "grad_norm": 0.2097524255514145,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.7552,
+      "step": 210
+    },
+    {
+      "epoch": 0.08471313053523297,
+      "grad_norm": 0.1747211515903473,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.7407,
+      "step": 220
+    },
+    {
+      "epoch": 0.08856372737774355,
+      "grad_norm": 0.1804259866476059,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.7374,
+      "step": 230
+    },
+    {
+      "epoch": 0.09241432422025414,
+      "grad_norm": 0.18586483597755432,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.7335,
+      "step": 240
+    },
+    {
+      "epoch": 0.09626492106276473,
+      "grad_norm": 0.19301919639110565,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.7508,
+      "step": 250
+    },
+    {
+      "epoch": 0.10011551790527531,
+      "grad_norm": 0.1669822335243225,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.7471,
+      "step": 260
+    },
+    {
+      "epoch": 0.1039661147477859,
+      "grad_norm": 0.17899902164936066,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.7301,
+      "step": 270
+    },
+    {
+      "epoch": 0.1078167115902965,
+      "grad_norm": 0.17165543138980865,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.727,
+      "step": 280
+    },
+    {
+      "epoch": 0.11166730843280709,
+      "grad_norm": 0.17960181832313538,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.7586,
+      "step": 290
+    },
+    {
+      "epoch": 0.11551790527531768,
+      "grad_norm": 0.16608622670173645,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.718,
+      "step": 300
+    },
+    {
+      "epoch": 0.11936850211782826,
+      "grad_norm": 0.1665564924478531,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.7224,
+      "step": 310
+    },
+    {
+      "epoch": 0.12321909896033885,
+      "grad_norm": 0.18018142879009247,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.7348,
+      "step": 320
+    },
+    {
+      "epoch": 0.12706969580284944,
+      "grad_norm": 0.17126788198947906,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.7327,
+      "step": 330
+    },
+    {
+      "epoch": 0.13092029264536004,
+      "grad_norm": 0.1734135001897812,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.7363,
+      "step": 340
+    },
+    {
+      "epoch": 0.1347708894878706,
+      "grad_norm": 0.19071175158023834,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.7428,
+      "step": 350
+    },
+    {
+      "epoch": 0.1386214863303812,
+      "grad_norm": 0.18125326931476593,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.7256,
+      "step": 360
+    },
+    {
+      "epoch": 0.1424720831728918,
+      "grad_norm": 0.20351630449295044,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.7545,
+      "step": 370
+    },
+    {
+      "epoch": 0.14632268001540238,
+      "grad_norm": 0.16795413196086884,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.7192,
+      "step": 380
+    },
+    {
+      "epoch": 0.15017327685791299,
+      "grad_norm": 0.17863358557224274,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.7186,
+      "step": 390
+    },
+    {
+      "epoch": 0.15402387370042356,
+      "grad_norm": 0.1602666676044464,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.7259,
+      "step": 400
+    },
+    {
+      "epoch": 0.15787447054293416,
+      "grad_norm": 0.18391664326190948,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.7213,
+      "step": 410
+    },
+    {
+      "epoch": 0.16172506738544473,
+      "grad_norm": 0.18419398367404938,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.7399,
+      "step": 420
+    },
+    {
+      "epoch": 0.16557566422795533,
+      "grad_norm": 0.1883566528558731,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.7231,
+      "step": 430
+    },
+    {
+      "epoch": 0.16942626107046593,
+      "grad_norm": 0.16978995501995087,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.725,
+      "step": 440
+    },
+    {
+      "epoch": 0.1732768579129765,
+      "grad_norm": 0.17612241208553314,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7127,
+      "step": 450
+    },
+    {
+      "epoch": 0.1771274547554871,
+      "grad_norm": 0.18710066378116608,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.7216,
+      "step": 460
+    },
+    {
+      "epoch": 0.18097805159799768,
+      "grad_norm": 0.16449962556362152,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.7236,
+      "step": 470
+    },
+    {
+      "epoch": 0.18482864844050828,
+      "grad_norm": 0.18440745770931244,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.7194,
+      "step": 480
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 0.1681339144706726,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.7172,
+      "step": 490
+    },
+    {
+      "epoch": 0.19252984212552945,
+      "grad_norm": 0.16043739020824432,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.7226,
+      "step": 500
+    },
+    {
+      "epoch": 0.19638043896804006,
+      "grad_norm": 0.17838488519191742,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7096,
+      "step": 510
+    },
+    {
+      "epoch": 0.20023103581055063,
+      "grad_norm": 0.1773468405008316,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.7328,
+      "step": 520
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.18085701763629913,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.7178,
+      "step": 530
+    },
+    {
+      "epoch": 0.2079322294955718,
+      "grad_norm": 0.1799478679895401,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.7264,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117828263380824,
+      "grad_norm": 0.17123673856258392,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.7351,
+      "step": 550
+    },
+    {
+      "epoch": 0.215633423180593,
+      "grad_norm": 0.17717215418815613,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.7351,
+      "step": 560
+    },
+    {
+      "epoch": 0.21948402002310358,
+      "grad_norm": 0.19180689752101898,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.7444,
+      "step": 570
+    },
+    {
+      "epoch": 0.22333461686561418,
+      "grad_norm": 0.18037578463554382,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.7163,
+      "step": 580
+    },
+    {
+      "epoch": 0.22718521370812475,
+      "grad_norm": 0.1682267040014267,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.729,
+      "step": 590
+    },
+    {
+      "epoch": 0.23103581055063535,
+      "grad_norm": 0.1594855785369873,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.7262,
+      "step": 600
+    },
+    {
+      "epoch": 0.23488640739314592,
+      "grad_norm": 0.18331752717494965,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.7462,
+      "step": 610
+    },
+    {
+      "epoch": 0.23873700423565652,
+      "grad_norm": 0.1678193211555481,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.7242,
+      "step": 620
+    },
+    {
+      "epoch": 0.24258760107816713,
+      "grad_norm": 0.17123256623744965,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.7365,
+      "step": 630
+    },
+    {
+      "epoch": 0.2464381979206777,
+      "grad_norm": 0.17702975869178772,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.739,
+      "step": 640
+    },
+    {
+      "epoch": 0.25028879476318827,
+      "grad_norm": 0.16033869981765747,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.6971,
+      "step": 650
+    },
+    {
+      "epoch": 0.25413939160569887,
+      "grad_norm": 0.1762455701828003,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.7191,
+      "step": 660
+    },
+    {
+      "epoch": 0.2579899884482095,
+      "grad_norm": 0.17223264276981354,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.7334,
+      "step": 670
+    },
+    {
+      "epoch": 0.2618405852907201,
+      "grad_norm": 0.1584424078464508,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7115,
+      "step": 680
+    },
+    {
+      "epoch": 0.2656911821332307,
+      "grad_norm": 0.17170844972133636,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.7208,
+      "step": 690
+    },
+    {
+      "epoch": 0.2695417789757412,
+      "grad_norm": 0.1763196587562561,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.7343,
+      "step": 700
+    },
+    {
+      "epoch": 0.2733923758182518,
+      "grad_norm": 0.16385102272033691,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7177,
+      "step": 710
+    },
+    {
+      "epoch": 0.2772429726607624,
+      "grad_norm": 0.16625148057937622,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7195,
+      "step": 720
+    },
+    {
+      "epoch": 0.281093569503273,
+      "grad_norm": 0.176108255982399,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.7251,
+      "step": 730
+    },
+    {
+      "epoch": 0.2849441663457836,
+      "grad_norm": 0.1754191517829895,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7122,
+      "step": 740
+    },
+    {
+      "epoch": 0.28879476318829417,
+      "grad_norm": 0.15761268138885498,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7105,
+      "step": 750
+    },
+    {
+      "epoch": 0.29264536003080477,
+      "grad_norm": 0.16691575944423676,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7051,
+      "step": 760
+    },
+    {
+      "epoch": 0.29649595687331537,
+      "grad_norm": 0.14969255030155182,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.7259,
+      "step": 770
+    },
+    {
+      "epoch": 0.30034655371582597,
+      "grad_norm": 0.17684991657733917,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.721,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041971505583365,
+      "grad_norm": 0.17436353862285614,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7022,
+      "step": 790
+    },
+    {
+      "epoch": 0.3080477474008471,
+      "grad_norm": 0.17761683464050293,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.7233,
+      "step": 800
+    },
+    {
+      "epoch": 0.3118983442433577,
+      "grad_norm": 0.15919841825962067,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7208,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157489410858683,
+      "grad_norm": 0.16602933406829834,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.7182,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195995379283789,
+      "grad_norm": 0.17026099562644958,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.7047,
+      "step": 830
+    },
+    {
+      "epoch": 0.32345013477088946,
+      "grad_norm": 0.16666896641254425,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.7061,
+      "step": 840
+    },
+    {
+      "epoch": 0.32730073161340006,
+      "grad_norm": 0.15952461957931519,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.7179,
+      "step": 850
+    },
+    {
+      "epoch": 0.33115132845591067,
+      "grad_norm": 0.17218954861164093,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7077,
+      "step": 860
+    },
+    {
+      "epoch": 0.33500192529842127,
+      "grad_norm": 0.1634567230939865,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7097,
+      "step": 870
+    },
+    {
+      "epoch": 0.33885252214093187,
+      "grad_norm": 0.17217908799648285,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.714,
+      "step": 880
+    },
+    {
+      "epoch": 0.3427031189834424,
+      "grad_norm": 0.17921409010887146,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7088,
+      "step": 890
+    },
+    {
+      "epoch": 0.346553715825953,
+      "grad_norm": 0.1571296602487564,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3504043126684636,
+      "grad_norm": 0.18973281979560852,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.6981,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542549095109742,
+      "grad_norm": 0.16592420637607574,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7093,
+      "step": 920
+    },
+    {
+      "epoch": 0.3581055063534848,
+      "grad_norm": 0.18421074748039246,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.6895,
+      "step": 930
+    },
+    {
+      "epoch": 0.36195610319599536,
+      "grad_norm": 0.1674077957868576,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.7201,
+      "step": 940
+    },
+    {
+      "epoch": 0.36580670003850596,
+      "grad_norm": 0.1724046766757965,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.7385,
+      "step": 950
+    },
+    {
+      "epoch": 0.36965729688101656,
+      "grad_norm": 0.16487306356430054,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7321,
+      "step": 960
+    },
+    {
+      "epoch": 0.37350789372352716,
+      "grad_norm": 0.15993347764015198,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.699,
+      "step": 970
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.16850320994853973,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7119,
+      "step": 980
+    },
+    {
+      "epoch": 0.3812090874085483,
+      "grad_norm": 0.1757180243730545,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.6942,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850596842510589,
+      "grad_norm": 0.17606504261493683,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.7092,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3889102810935695,
+      "grad_norm": 0.1618117392063141,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.7295,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3927608779360801,
+      "grad_norm": 0.17762435972690582,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.7254,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39661147477859066,
+      "grad_norm": 0.15181240439414978,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7225,
+      "step": 1030
+    },
+    {
+      "epoch": 0.40046207162110126,
+      "grad_norm": 0.17211619019508362,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.7091,
+      "step": 1040
+    },
+    {
+      "epoch": 0.40431266846361186,
+      "grad_norm": 0.1565019190311432,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.7029,
+      "step": 1050
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.15677987039089203,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.7099,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41201386214863306,
+      "grad_norm": 0.1699492335319519,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.6998,
+      "step": 1070
+    },
+    {
+      "epoch": 0.4158644589911436,
+      "grad_norm": 0.1543174684047699,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.7285,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4197150558336542,
+      "grad_norm": 0.18467400968074799,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7108,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235656526761648,
+      "grad_norm": 0.17130132019519806,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.7233,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4274162495186754,
+      "grad_norm": 0.17400452494621277,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.7131,
+      "step": 1110
+    },
+    {
+      "epoch": 0.431266846361186,
+      "grad_norm": 0.17654776573181152,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7118,
+      "step": 1120
+    },
+    {
+      "epoch": 0.43511744320369655,
+      "grad_norm": 0.17512840032577515,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.692,
+      "step": 1130
+    },
+    {
+      "epoch": 0.43896804004620715,
+      "grad_norm": 0.1833694577217102,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7175,
+      "step": 1140
+    },
+    {
+      "epoch": 0.44281863688871775,
+      "grad_norm": 0.16677677631378174,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7005,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44666923373122835,
+      "grad_norm": 0.2014331817626953,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.7319,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45051983057373896,
+      "grad_norm": 0.1611153483390808,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.7371,
+      "step": 1170
+    },
+    {
+      "epoch": 0.4543704274162495,
+      "grad_norm": 0.16768869757652283,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7194,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4582210242587601,
+      "grad_norm": 0.155109703540802,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.6919,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4620716211012707,
+      "grad_norm": 0.16766905784606934,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7033,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4659222179437813,
+      "grad_norm": 0.16366654634475708,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.702,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46977281478629185,
+      "grad_norm": 0.17265798151493073,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7262,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47362341162880245,
+      "grad_norm": 0.16238486766815186,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7237,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47747400847131305,
+      "grad_norm": 0.1602874994277954,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7024,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48132460531382365,
+      "grad_norm": 0.1582975685596466,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.6922,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48517520215633425,
+      "grad_norm": 0.18967410922050476,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7091,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4890257989988448,
+      "grad_norm": 0.17751871049404144,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.6836,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928763958413554,
+      "grad_norm": 0.17519156634807587,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7027,
+      "step": 1280
+    },
+    {
+      "epoch": 0.496726992683866,
+      "grad_norm": 0.15830343961715698,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.7138,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005775895263765,
+      "grad_norm": 0.15932805836200714,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7034,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5044281863688872,
+      "grad_norm": 0.17435204982757568,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.7267,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082787832113977,
+      "grad_norm": 0.17649157345294952,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.6928,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5121293800539084,
+      "grad_norm": 0.1864655464887619,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.6997,
+      "step": 1330
+    },
+    {
+      "epoch": 0.515979976896419,
+      "grad_norm": 0.1710236668586731,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.707,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5198305737389295,
+      "grad_norm": 0.16371099650859833,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7086,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236811705814401,
+      "grad_norm": 0.18387076258659363,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.7194,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5275317674239507,
+      "grad_norm": 0.1674361377954483,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.7102,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313823642664613,
+      "grad_norm": 0.15942128002643585,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.7253,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5352329611089719,
+      "grad_norm": 0.17368805408477783,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7002,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390835579514824,
+      "grad_norm": 0.16207954287528992,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5429341547939931,
+      "grad_norm": 0.17600366473197937,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7226,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467847516365036,
+      "grad_norm": 0.1744917929172516,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7018,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5506353484790143,
+      "grad_norm": 0.1701734960079193,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.7156,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544859453215248,
+      "grad_norm": 0.17661939561367035,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7191,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5583365421640354,
+      "grad_norm": 0.17580360174179077,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7021,
+      "step": 1450
+    },
+    {
+      "epoch": 0.562187139006546,
+      "grad_norm": 0.1640946865081787,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7066,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 0.16538135707378387,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7005,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698883326915672,
+      "grad_norm": 0.16469015181064606,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.6968,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5737389295340778,
+      "grad_norm": 0.16463309526443481,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7045,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775895263765883,
+      "grad_norm": 0.1698637455701828,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.718,
+      "step": 1500
+    },
+    {
+      "epoch": 0.581440123219099,
+      "grad_norm": 0.16468732059001923,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7099,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852907200616095,
+      "grad_norm": 0.17476193606853485,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.717,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5891413169041202,
+      "grad_norm": 0.161778524518013,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.7169,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929919137466307,
+      "grad_norm": 0.1708841770887375,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.7218,
+      "step": 1540
+    },
+    {
+      "epoch": 0.5968425105891413,
+      "grad_norm": 0.15906748175621033,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.7073,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006931074316519,
+      "grad_norm": 0.15872354805469513,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7153,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6045437042741625,
+      "grad_norm": 0.17402592301368713,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.7241,
+      "step": 1570
+    },
+    {
+      "epoch": 0.608394301116673,
+      "grad_norm": 0.17862671613693237,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.7152,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.14770978689193726,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.7113,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160954948016942,
+      "grad_norm": 0.16436228156089783,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7083,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6199460916442049,
+      "grad_norm": 0.15461604297161102,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.6844,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6237966884867154,
+      "grad_norm": 0.17172633111476898,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.6867,
+      "step": 1620
+    },
+    {
+      "epoch": 0.627647285329226,
+      "grad_norm": 0.16525618731975555,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7119,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314978821717366,
+      "grad_norm": 0.1575607806444168,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7018,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6353484790142472,
+      "grad_norm": 0.16875173151493073,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7175,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391990758567578,
+      "grad_norm": 0.16198505461215973,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.6963,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6430496726992684,
+      "grad_norm": 0.17602263391017914,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.7142,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6469002695417789,
+      "grad_norm": 0.16905713081359863,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7028,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6507508663842896,
+      "grad_norm": 0.16281872987747192,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.6989,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6546014632268001,
+      "grad_norm": 0.159073606133461,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7004,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6584520600693108,
+      "grad_norm": 0.17302295565605164,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7094,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6623026569118213,
+      "grad_norm": 0.17963649332523346,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7026,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6661532537543319,
+      "grad_norm": 0.18635277450084686,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.7032,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6700038505968425,
+      "grad_norm": 0.16692113876342773,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7131,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6738544474393531,
+      "grad_norm": 0.16257011890411377,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.71,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6777050442818637,
+      "grad_norm": 0.15963806211948395,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.6992,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6815556411243743,
+      "grad_norm": 0.1717417985200882,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.7371,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6854062379668848,
+      "grad_norm": 0.16468502581119537,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7126,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6892568348093955,
+      "grad_norm": 0.17600858211517334,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.7281,
+      "step": 1790
+    },
+    {
+      "epoch": 0.693107431651906,
+      "grad_norm": 0.1564195454120636,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.6965,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6969580284944167,
+      "grad_norm": 0.1731816828250885,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.6904,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7008086253369272,
+      "grad_norm": 0.15967042744159698,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.712,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7046592221794378,
+      "grad_norm": 0.17101597785949707,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.6968,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7085098190219484,
+      "grad_norm": 0.16217100620269775,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7024,
+      "step": 1840
+    },
+    {
+      "epoch": 0.712360415864459,
+      "grad_norm": 0.1737545281648636,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.7183,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7162110127069696,
+      "grad_norm": 0.16118942201137543,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7144,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7200616095494802,
+      "grad_norm": 0.16470012068748474,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.705,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7239122063919907,
+      "grad_norm": 0.16197429597377777,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7155,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7277628032345014,
+      "grad_norm": 0.1663857400417328,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7007,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7316134000770119,
+      "grad_norm": 0.17808210849761963,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7126,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7354639969195226,
+      "grad_norm": 0.1609569638967514,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 0.7393145937620331,
+      "grad_norm": 0.16338875889778137,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.6999,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7431651906045437,
+      "grad_norm": 0.17774735391139984,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7143,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7470157874470543,
+      "grad_norm": 0.15919660031795502,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.7183,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7508663842895649,
+      "grad_norm": 0.16879403591156006,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.17776603996753693,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7249,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7585675779745861,
+      "grad_norm": 0.1693299561738968,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7146,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7624181748170966,
+      "grad_norm": 0.18018046021461487,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7148,
+      "step": 1980
+    },
+    {
+      "epoch": 0.7662687716596073,
+      "grad_norm": 0.17742303013801575,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.704,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7701193685021178,
+      "grad_norm": 0.16927465796470642,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7041,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7739699653446284,
+      "grad_norm": 0.1587079018354416,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.713,
+      "step": 2010
+    },
+    {
+      "epoch": 0.777820562187139,
+      "grad_norm": 0.15766935050487518,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.6911,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7816711590296496,
+      "grad_norm": 0.1625840663909912,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.6856,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7855217558721602,
+      "grad_norm": 0.16537828743457794,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.701,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7893723527146708,
+      "grad_norm": 0.1575583666563034,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7038,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7932229495571813,
+      "grad_norm": 0.15075618028640747,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.688,
+      "step": 2060
+    },
+    {
+      "epoch": 0.797073546399692,
+      "grad_norm": 0.16791854798793793,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.7033,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8009241432422025,
+      "grad_norm": 0.1602427363395691,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.682,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8047747400847132,
+      "grad_norm": 0.1593937873840332,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7102,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8086253369272237,
+      "grad_norm": 0.1535065621137619,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.7001,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8124759337697343,
+      "grad_norm": 0.16188828647136688,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7076,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.1824655532836914,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7216,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8201771274547555,
+      "grad_norm": 0.16509822010993958,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7011,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8240277242972661,
+      "grad_norm": 0.1771237552165985,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7046,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8278783211397767,
+      "grad_norm": 0.16009916365146637,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.6914,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8317289179822872,
+      "grad_norm": 0.16029998660087585,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7128,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8355795148247979,
+      "grad_norm": 0.1671282947063446,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7063,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8394301116673084,
+      "grad_norm": 0.161812886595726,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7035,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8432807085098191,
+      "grad_norm": 0.17220066487789154,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.7009,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8471313053523296,
+      "grad_norm": 0.16964896023273468,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.706,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8509819021948402,
+      "grad_norm": 0.15788240730762482,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.6771,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8548324990373508,
+      "grad_norm": 0.15693308413028717,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7093,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586830958798614,
+      "grad_norm": 0.1780892014503479,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7034,
+      "step": 2230
+    },
+    {
+      "epoch": 0.862533692722372,
+      "grad_norm": 0.15874965488910675,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.7152,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663842895648826,
+      "grad_norm": 0.16851408779621124,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7021,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8702348864073931,
+      "grad_norm": 0.20063835382461548,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.6849,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740854832499038,
+      "grad_norm": 0.1628538817167282,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7018,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8779360800924143,
+      "grad_norm": 0.16099168360233307,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7126,
+      "step": 2280
+    },
+    {
+      "epoch": 0.881786676934925,
+      "grad_norm": 0.1615016907453537,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.7071,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8856372737774355,
+      "grad_norm": 0.1560729444026947,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.6931,
+      "step": 2300
+    },
+    {
+      "epoch": 0.889487870619946,
+      "grad_norm": 0.16066791117191315,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7046,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8933384674624567,
+      "grad_norm": 0.15619836747646332,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7052,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971890643049673,
+      "grad_norm": 0.16742493212223053,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7161,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9010396611474779,
+      "grad_norm": 0.15788961946964264,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7064,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048902579899885,
+      "grad_norm": 0.16814817488193512,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.6896,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908740854832499,
+      "grad_norm": 0.16063177585601807,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7027,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125914516750097,
+      "grad_norm": 0.17853383719921112,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.6956,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9164420485175202,
+      "grad_norm": 0.15843184292316437,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7095,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202926453600309,
+      "grad_norm": 0.1638718992471695,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7224,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9241432422025414,
+      "grad_norm": 0.1806347370147705,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7151,
+      "step": 2400
+    },
+    {
+      "epoch": 0.927993839045052,
+      "grad_norm": 0.15908129513263702,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.6912,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9318444358875626,
+      "grad_norm": 0.1587260514497757,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7208,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9356950327300732,
+      "grad_norm": 0.16640456020832062,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.7153,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9395456295725837,
+      "grad_norm": 0.1634569615125656,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7019,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 0.16659069061279297,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.6906,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9472468232576049,
+      "grad_norm": 0.1767168939113617,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7184,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510974201001156,
+      "grad_norm": 0.17714691162109375,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7144,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9549480169426261,
+      "grad_norm": 0.16267523169517517,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.6996,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587986137851366,
+      "grad_norm": 0.16102389991283417,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.701,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9626492106276473,
+      "grad_norm": 0.16306807100772858,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.706,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664998074701578,
+      "grad_norm": 0.1571447253227234,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7035,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9703504043126685,
+      "grad_norm": 0.16160961985588074,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7191,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974201001155179,
+      "grad_norm": 0.17240826785564423,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.6979,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9780515979976896,
+      "grad_norm": 0.155216783285141,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7003,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9819021948402002,
+      "grad_norm": 0.15195542573928833,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7137,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9857527916827108,
+      "grad_norm": 0.15452726185321808,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.6976,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9896033885252215,
+      "grad_norm": 0.16271187365055084,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.6962,
+      "step": 2570
+    },
+    {
+      "epoch": 0.993453985367732,
+      "grad_norm": 0.15679427981376648,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.684,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9973045822102425,
+      "grad_norm": 0.1723206788301468,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7203,
+      "step": 2590
+    },
+    {
+      "epoch": 1.0,
+      "step": 2597,
+      "total_flos": 1.2144495374945485e+19,
+      "train_loss": 0.7219763918477479,
+      "train_runtime": 19732.9714,
+      "train_samples_per_second": 33.695,
+      "train_steps_per_second": 0.132
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 584317136,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2144495374945485e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/smollm2/mc2_g14_378/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7210aebf10e0fbe7f092845f640355df75cad8a9ebee7b390809bc4326941297
+size 6264

continuous/smollm2/mc2_g14_378/pretrain/config.json

@@ -0,0 +1,70 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_hidden_size": 1664,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-bigG-14-worldwide-378",
+  "mm_vision_tower_lr": null,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_g14_378.pt",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_g14_378/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a176d2930fc5c4b549a4a2a0d2ebc0584b5808d52861650bb8db07a114b2f9
+size 30427192

continuous/smollm2/mc2_g14_378/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.9234743714332581,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 4.3272,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.10950742661952972,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 3.0786,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.059733327478170395,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 2.8569,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.03740810230374336,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 2.7832,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.03387226536870003,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 2.7603,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.05531882122159004,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 2.7283,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.06087932363152504,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 2.7014,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.08693356066942215,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 2.6642,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.11093096435070038,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 2.6265,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.08481546491384506,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 2.5938,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.11996915191411972,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 2.5564,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.08445097506046295,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 2.5299,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.10162199288606644,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 2.4868,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.08844240754842758,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 2.4539,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.10214713960886002,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 2.4366,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.08069880306720734,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 2.4021,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.07671406865119934,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 2.3827,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.08844546228647232,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 2.3609,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.07687392085790634,
+      "learning_rate": 0.000779204504653894,
+      "loss": 2.339,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.08689157664775848,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 2.3036,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.07402586936950684,
+      "learning_rate": 0.00072685988254984,
+      "loss": 2.2879,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.09753783792257309,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 2.287,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.08403682708740234,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 2.2662,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.06928866356611252,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 2.2474,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.08228620141744614,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 2.2317,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.08865690231323242,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 2.2256,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.08555923402309418,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 2.1922,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07436063140630722,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 2.1811,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.07486726343631744,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 2.1528,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.07436061650514603,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 2.1384,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.12279442697763443,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 2.1329,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.07548742741346359,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 2.1208,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.07632739841938019,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 2.0977,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.07257174700498581,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 2.0923,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.07511129975318909,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 2.0836,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.08284367620944977,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 2.0816,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.07023733109235764,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 2.0713,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.06845036894083023,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 2.0726,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.06579513847827911,
+      "learning_rate": 0.000208323983828828,
+      "loss": 2.0615,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.06709083169698715,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 2.0555,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.0725678876042366,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 2.0602,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.07150682061910629,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 2.051,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.06403055042028427,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 2.0486,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.06751960515975952,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 2.0535,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.06337030977010727,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 2.0457,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.060607243329286575,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 2.0414,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.06193726137280464,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 2.0334,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.058560580015182495,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 2.0377,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.05581305921077728,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 2.0424,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.05895138159394264,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 2.0453,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.05919021740555763,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 2.0387,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.05782381445169449,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 2.0352,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.05842979624867439,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 2.0365,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.05694400519132614,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 2.0336,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 6.91255292792406e+17,
+      "train_loss": 2.3133670631898653,
+      "train_runtime": 4818.7348,
+      "train_samples_per_second": 115.825,
+      "train_steps_per_second": 0.113
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 33258880,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.91255292792406e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/smollm2/mc2_h14_378/finetune/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

continuous/smollm2/mc2_h14_378/finetune/config.json

@@ -0,0 +1,70 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_hidden_size": 1280,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-H-14-worldwide-378",
+  "mm_vision_tower_lr": null,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_h14_378.pt",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_h14_378/finetune/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.57.6"
+}

continuous/smollm2/mc2_h14_378/finetune/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dac1fe862277c9c5ea705e81d89fefc22a5f9c6ad7d6a5fb2c1c9304d5c9fa2
+size 4916806248

continuous/smollm2/mc2_h14_378/finetune/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

continuous/smollm2/mc2_h14_378/finetune/tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_h14_378/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850596842510589,
+      "grad_norm": 3.207995653152466,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 1.2731,
+      "step": 10
+    },
+    {
+      "epoch": 0.007701193685021178,
+      "grad_norm": 2.0629212856292725,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.1233,
+      "step": 20
+    },
+    {
+      "epoch": 0.011551790527531768,
+      "grad_norm": 1.9393634796142578,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 0.9968,
+      "step": 30
+    },
+    {
+      "epoch": 0.015402387370042356,
+      "grad_norm": 1.310421347618103,
+      "learning_rate": 5e-06,
+      "loss": 0.9548,
+      "step": 40
+    },
+    {
+      "epoch": 0.019252984212552945,
+      "grad_norm": 1.2892119884490967,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 0.9455,
+      "step": 50
+    },
+    {
+      "epoch": 0.023103581055063535,
+      "grad_norm": 0.2893568277359009,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.8769,
+      "step": 60
+    },
+    {
+      "epoch": 0.026954177897574125,
+      "grad_norm": 0.24181459844112396,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.8304,
+      "step": 70
+    },
+    {
+      "epoch": 0.030804774740084712,
+      "grad_norm": 0.2326192557811737,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.844,
+      "step": 80
+    },
+    {
+      "epoch": 0.0346553715825953,
+      "grad_norm": 0.2370227724313736,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.8287,
+      "step": 90
+    },
+    {
+      "epoch": 0.03850596842510589,
+      "grad_norm": 0.20309659838676453,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.7976,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235656526761648,
+      "grad_norm": 0.2133292257785797,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.7885,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620716211012707,
+      "grad_norm": 0.23181907832622528,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8085,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005775895263766,
+      "grad_norm": 0.21398353576660156,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.785,
+      "step": 130
+    },
+    {
+      "epoch": 0.05390835579514825,
+      "grad_norm": 0.2217267006635666,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.799,
+      "step": 140
+    },
+    {
+      "epoch": 0.05775895263765884,
+      "grad_norm": 0.23109984397888184,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.7765,
+      "step": 150
+    },
+    {
+      "epoch": 0.061609549480169425,
+      "grad_norm": 0.2140430212020874,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.782,
+      "step": 160
+    },
+    {
+      "epoch": 0.06546014632268002,
+      "grad_norm": 0.2006809264421463,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.7822,
+      "step": 170
+    },
+    {
+      "epoch": 0.0693107431651906,
+      "grad_norm": 0.19803579151630402,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.815,
+      "step": 180
+    },
+    {
+      "epoch": 0.07316134000770119,
+      "grad_norm": 0.2167932093143463,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8011,
+      "step": 190
+    },
+    {
+      "epoch": 0.07701193685021178,
+      "grad_norm": 0.2104213684797287,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.7997,
+      "step": 200
+    },
+    {
+      "epoch": 0.08086253369272237,
+      "grad_norm": 0.2023148089647293,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.786,
+      "step": 210
+    },
+    {
+      "epoch": 0.08471313053523297,
+      "grad_norm": 0.2011352777481079,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.776,
+      "step": 220
+    },
+    {
+      "epoch": 0.08856372737774355,
+      "grad_norm": 0.19576169550418854,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.7724,
+      "step": 230
+    },
+    {
+      "epoch": 0.09241432422025414,
+      "grad_norm": 0.2062547206878662,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.7658,
+      "step": 240
+    },
+    {
+      "epoch": 0.09626492106276473,
+      "grad_norm": 0.21466225385665894,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.7838,
+      "step": 250
+    },
+    {
+      "epoch": 0.10011551790527531,
+      "grad_norm": 0.20452089607715607,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.7816,
+      "step": 260
+    },
+    {
+      "epoch": 0.1039661147477859,
+      "grad_norm": 0.1935971975326538,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.7637,
+      "step": 270
+    },
+    {
+      "epoch": 0.1078167115902965,
+      "grad_norm": 0.18877024948596954,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.7617,
+      "step": 280
+    },
+    {
+      "epoch": 0.11166730843280709,
+      "grad_norm": 0.200346902012825,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.7928,
+      "step": 290
+    },
+    {
+      "epoch": 0.11551790527531768,
+      "grad_norm": 0.1905466467142105,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.7517,
+      "step": 300
+    },
+    {
+      "epoch": 0.11936850211782826,
+      "grad_norm": 0.18825288116931915,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.7564,
+      "step": 310
+    },
+    {
+      "epoch": 0.12321909896033885,
+      "grad_norm": 0.1949509084224701,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.7672,
+      "step": 320
+    },
+    {
+      "epoch": 0.12706969580284944,
+      "grad_norm": 0.1977345049381256,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.7678,
+      "step": 330
+    },
+    {
+      "epoch": 0.13092029264536004,
+      "grad_norm": 0.1860123574733734,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.7709,
+      "step": 340
+    },
+    {
+      "epoch": 0.1347708894878706,
+      "grad_norm": 0.20477111637592316,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.776,
+      "step": 350
+    },
+    {
+      "epoch": 0.1386214863303812,
+      "grad_norm": 0.18900775909423828,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.7574,
+      "step": 360
+    },
+    {
+      "epoch": 0.1424720831728918,
+      "grad_norm": 0.19917947053909302,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.7859,
+      "step": 370
+    },
+    {
+      "epoch": 0.14632268001540238,
+      "grad_norm": 0.17502111196517944,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.7505,
+      "step": 380
+    },
+    {
+      "epoch": 0.15017327685791299,
+      "grad_norm": 0.1949923038482666,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.7533,
+      "step": 390
+    },
+    {
+      "epoch": 0.15402387370042356,
+      "grad_norm": 0.18355748057365417,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.7602,
+      "step": 400
+    },
+    {
+      "epoch": 0.15787447054293416,
+      "grad_norm": 0.19785940647125244,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.7567,
+      "step": 410
+    },
+    {
+      "epoch": 0.16172506738544473,
+      "grad_norm": 0.19077087938785553,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.7719,
+      "step": 420
+    },
+    {
+      "epoch": 0.16557566422795533,
+      "grad_norm": 0.19348032772541046,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.7531,
+      "step": 430
+    },
+    {
+      "epoch": 0.16942626107046593,
+      "grad_norm": 0.18355987966060638,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.759,
+      "step": 440
+    },
+    {
+      "epoch": 0.1732768579129765,
+      "grad_norm": 0.20343996584415436,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7459,
+      "step": 450
+    },
+    {
+      "epoch": 0.1771274547554871,
+      "grad_norm": 0.2309308499097824,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.7547,
+      "step": 460
+    },
+    {
+      "epoch": 0.18097805159799768,
+      "grad_norm": 0.1783764362335205,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.7573,
+      "step": 470
+    },
+    {
+      "epoch": 0.18482864844050828,
+      "grad_norm": 0.19903789460659027,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.7553,
+      "step": 480
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 0.17893461883068085,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.7502,
+      "step": 490
+    },
+    {
+      "epoch": 0.19252984212552945,
+      "grad_norm": 0.17553719878196716,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.7538,
+      "step": 500
+    },
+    {
+      "epoch": 0.19638043896804006,
+      "grad_norm": 0.19792483747005463,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7427,
+      "step": 510
+    },
+    {
+      "epoch": 0.20023103581055063,
+      "grad_norm": 0.1874416023492813,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.766,
+      "step": 520
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.18930910527706146,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.7499,
+      "step": 530
+    },
+    {
+      "epoch": 0.2079322294955718,
+      "grad_norm": 0.19492065906524658,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.7594,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117828263380824,
+      "grad_norm": 0.1853386014699936,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.7645,
+      "step": 550
+    },
+    {
+      "epoch": 0.215633423180593,
+      "grad_norm": 0.1939723640680313,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.7669,
+      "step": 560
+    },
+    {
+      "epoch": 0.21948402002310358,
+      "grad_norm": 0.21476595103740692,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.7817,
+      "step": 570
+    },
+    {
+      "epoch": 0.22333461686561418,
+      "grad_norm": 0.20793549716472626,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.7492,
+      "step": 580
+    },
+    {
+      "epoch": 0.22718521370812475,
+      "grad_norm": 0.18323729932308197,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.7642,
+      "step": 590
+    },
+    {
+      "epoch": 0.23103581055063535,
+      "grad_norm": 0.17072497308254242,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.7607,
+      "step": 600
+    },
+    {
+      "epoch": 0.23488640739314592,
+      "grad_norm": 0.1988225281238556,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.7785,
+      "step": 610
+    },
+    {
+      "epoch": 0.23873700423565652,
+      "grad_norm": 0.17649339139461517,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.7586,
+      "step": 620
+    },
+    {
+      "epoch": 0.24258760107816713,
+      "grad_norm": 0.18934305012226105,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.7706,
+      "step": 630
+    },
+    {
+      "epoch": 0.2464381979206777,
+      "grad_norm": 0.18979403376579285,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.7682,
+      "step": 640
+    },
+    {
+      "epoch": 0.25028879476318827,
+      "grad_norm": 0.1676911860704422,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7284,
+      "step": 650
+    },
+    {
+      "epoch": 0.25413939160569887,
+      "grad_norm": 0.1924174278974533,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.7551,
+      "step": 660
+    },
+    {
+      "epoch": 0.2579899884482095,
+      "grad_norm": 0.18181052803993225,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.764,
+      "step": 670
+    },
+    {
+      "epoch": 0.2618405852907201,
+      "grad_norm": 0.17948457598686218,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7449,
+      "step": 680
+    },
+    {
+      "epoch": 0.2656911821332307,
+      "grad_norm": 0.18506313860416412,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.7546,
+      "step": 690
+    },
+    {
+      "epoch": 0.2695417789757412,
+      "grad_norm": 0.1932167261838913,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.767,
+      "step": 700
+    },
+    {
+      "epoch": 0.2733923758182518,
+      "grad_norm": 0.1711454689502716,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7481,
+      "step": 710
+    },
+    {
+      "epoch": 0.2772429726607624,
+      "grad_norm": 0.17263256013393402,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7498,
+      "step": 720
+    },
+    {
+      "epoch": 0.281093569503273,
+      "grad_norm": 0.18547183275222778,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.7587,
+      "step": 730
+    },
+    {
+      "epoch": 0.2849441663457836,
+      "grad_norm": 0.18588273227214813,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7452,
+      "step": 740
+    },
+    {
+      "epoch": 0.28879476318829417,
+      "grad_norm": 0.1728445291519165,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7423,
+      "step": 750
+    },
+    {
+      "epoch": 0.29264536003080477,
+      "grad_norm": 0.18142609298229218,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7384,
+      "step": 760
+    },
+    {
+      "epoch": 0.29649595687331537,
+      "grad_norm": 0.174064040184021,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.7579,
+      "step": 770
+    },
+    {
+      "epoch": 0.30034655371582597,
+      "grad_norm": 0.19061584770679474,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.7522,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041971505583365,
+      "grad_norm": 0.180818572640419,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7353,
+      "step": 790
+    },
+    {
+      "epoch": 0.3080477474008471,
+      "grad_norm": 0.20825153589248657,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.7572,
+      "step": 800
+    },
+    {
+      "epoch": 0.3118983442433577,
+      "grad_norm": 0.17631761729717255,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7548,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157489410858683,
+      "grad_norm": 0.18095295131206512,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.7516,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195995379283789,
+      "grad_norm": 0.18807555735111237,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.7398,
+      "step": 830
+    },
+    {
+      "epoch": 0.32345013477088946,
+      "grad_norm": 0.19048701226711273,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.7381,
+      "step": 840
+    },
+    {
+      "epoch": 0.32730073161340006,
+      "grad_norm": 0.18328005075454712,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.7498,
+      "step": 850
+    },
+    {
+      "epoch": 0.33115132845591067,
+      "grad_norm": 0.19163933396339417,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7403,
+      "step": 860
+    },
+    {
+      "epoch": 0.33500192529842127,
+      "grad_norm": 0.17682544887065887,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7431,
+      "step": 870
+    },
+    {
+      "epoch": 0.33885252214093187,
+      "grad_norm": 0.1858559250831604,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.7456,
+      "step": 880
+    },
+    {
+      "epoch": 0.3427031189834424,
+      "grad_norm": 0.1892724633216858,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7404,
+      "step": 890
+    },
+    {
+      "epoch": 0.346553715825953,
+      "grad_norm": 0.17160019278526306,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.7414,
+      "step": 900
+    },
+    {
+      "epoch": 0.3504043126684636,
+      "grad_norm": 0.2060266137123108,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.7323,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542549095109742,
+      "grad_norm": 0.1706419438123703,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.74,
+      "step": 920
+    },
+    {
+      "epoch": 0.3581055063534848,
+      "grad_norm": 0.2039312720298767,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7212,
+      "step": 930
+    },
+    {
+      "epoch": 0.36195610319599536,
+      "grad_norm": 0.18794319033622742,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.7523,
+      "step": 940
+    },
+    {
+      "epoch": 0.36580670003850596,
+      "grad_norm": 0.18742404878139496,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.7689,
+      "step": 950
+    },
+    {
+      "epoch": 0.36965729688101656,
+      "grad_norm": 0.18056932091712952,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7639,
+      "step": 960
+    },
+    {
+      "epoch": 0.37350789372352716,
+      "grad_norm": 0.17765051126480103,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7329,
+      "step": 970
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.18017221987247467,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7427,
+      "step": 980
+    },
+    {
+      "epoch": 0.3812090874085483,
+      "grad_norm": 0.1985270082950592,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7289,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850596842510589,
+      "grad_norm": 0.18635611236095428,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.74,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3889102810935695,
+      "grad_norm": 0.17533673346042633,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.761,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3927608779360801,
+      "grad_norm": 0.19712257385253906,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.7583,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39661147477859066,
+      "grad_norm": 0.1660699099302292,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7548,
+      "step": 1030
+    },
+    {
+      "epoch": 0.40046207162110126,
+      "grad_norm": 0.18632963299751282,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.7432,
+      "step": 1040
+    },
+    {
+      "epoch": 0.40431266846361186,
+      "grad_norm": 0.17112348973751068,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.17132440209388733,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.7432,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41201386214863306,
+      "grad_norm": 0.18323445320129395,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.7346,
+      "step": 1070
+    },
+    {
+      "epoch": 0.4158644589911436,
+      "grad_norm": 0.1690492182970047,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.7612,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4197150558336542,
+      "grad_norm": 0.1953308880329132,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7436,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235656526761648,
+      "grad_norm": 0.19419041275978088,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.7544,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4274162495186754,
+      "grad_norm": 0.18323619663715363,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.7466,
+      "step": 1110
+    },
+    {
+      "epoch": 0.431266846361186,
+      "grad_norm": 0.1980379968881607,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7449,
+      "step": 1120
+    },
+    {
+      "epoch": 0.43511744320369655,
+      "grad_norm": 0.18343961238861084,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7254,
+      "step": 1130
+    },
+    {
+      "epoch": 0.43896804004620715,
+      "grad_norm": 0.19485729932785034,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7503,
+      "step": 1140
+    },
+    {
+      "epoch": 0.44281863688871775,
+      "grad_norm": 0.1817959100008011,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7346,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44666923373122835,
+      "grad_norm": 0.2122112512588501,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.7643,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45051983057373896,
+      "grad_norm": 0.17962083220481873,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.7703,
+      "step": 1170
+    },
+    {
+      "epoch": 0.4543704274162495,
+      "grad_norm": 0.17979882657527924,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7503,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4582210242587601,
+      "grad_norm": 0.1763962060213089,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.727,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4620716211012707,
+      "grad_norm": 0.18285952508449554,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7359,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4659222179437813,
+      "grad_norm": 0.17617158591747284,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.7343,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46977281478629185,
+      "grad_norm": 0.19649508595466614,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7596,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47362341162880245,
+      "grad_norm": 0.17961232364177704,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7554,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47747400847131305,
+      "grad_norm": 0.19382347166538239,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7333,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48132460531382365,
+      "grad_norm": 0.1800498366355896,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7266,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48517520215633425,
+      "grad_norm": 0.19492872059345245,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7403,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4890257989988448,
+      "grad_norm": 0.19636720418930054,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7184,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928763958413554,
+      "grad_norm": 0.18290695548057556,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7341,
+      "step": 1280
+    },
+    {
+      "epoch": 0.496726992683866,
+      "grad_norm": 0.17381180822849274,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.7462,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005775895263765,
+      "grad_norm": 0.18229903280735016,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7362,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5044281863688872,
+      "grad_norm": 0.18806684017181396,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.7561,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082787832113977,
+      "grad_norm": 0.19440791010856628,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7257,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5121293800539084,
+      "grad_norm": 0.18755145370960236,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.7341,
+      "step": 1330
+    },
+    {
+      "epoch": 0.515979976896419,
+      "grad_norm": 0.18730378150939941,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7399,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5198305737389295,
+      "grad_norm": 0.1761074960231781,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.737,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236811705814401,
+      "grad_norm": 0.1994534432888031,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.7528,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5275317674239507,
+      "grad_norm": 0.18353396654129028,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.7443,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313823642664613,
+      "grad_norm": 0.1729428619146347,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.7592,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5352329611089719,
+      "grad_norm": 0.1855306774377823,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7335,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390835579514824,
+      "grad_norm": 0.1798240840435028,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7353,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5429341547939931,
+      "grad_norm": 0.19639213383197784,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7538,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467847516365036,
+      "grad_norm": 0.19579842686653137,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7368,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5506353484790143,
+      "grad_norm": 0.19055098295211792,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.7489,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544859453215248,
+      "grad_norm": 0.19388598203659058,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7503,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5583365421640354,
+      "grad_norm": 0.19282902777194977,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7335,
+      "step": 1450
+    },
+    {
+      "epoch": 0.562187139006546,
+      "grad_norm": 0.185003399848938,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7399,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 0.1873195320367813,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7342,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698883326915672,
+      "grad_norm": 0.1831091195344925,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7284,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5737389295340778,
+      "grad_norm": 0.18746259808540344,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7367,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775895263765883,
+      "grad_norm": 0.17984627187252045,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.749,
+      "step": 1500
+    },
+    {
+      "epoch": 0.581440123219099,
+      "grad_norm": 0.18162478506565094,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7416,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852907200616095,
+      "grad_norm": 0.18062885105609894,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.7498,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5891413169041202,
+      "grad_norm": 0.17723749577999115,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.7498,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929919137466307,
+      "grad_norm": 0.17871344089508057,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.7519,
+      "step": 1540
+    },
+    {
+      "epoch": 0.5968425105891413,
+      "grad_norm": 0.17040303349494934,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.7402,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006931074316519,
+      "grad_norm": 0.17505566775798798,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7499,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6045437042741625,
+      "grad_norm": 0.193471759557724,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.756,
+      "step": 1570
+    },
+    {
+      "epoch": 0.608394301116673,
+      "grad_norm": 0.19196824729442596,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.7493,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.16212783753871918,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.743,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160954948016942,
+      "grad_norm": 0.17772769927978516,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7399,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6199460916442049,
+      "grad_norm": 0.17606544494628906,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7184,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6237966884867154,
+      "grad_norm": 0.18334455788135529,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7189,
+      "step": 1620
+    },
+    {
+      "epoch": 0.627647285329226,
+      "grad_norm": 0.182767853140831,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7438,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314978821717366,
+      "grad_norm": 0.1688811182975769,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7356,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6353484790142472,
+      "grad_norm": 0.18522909283638,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7497,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391990758567578,
+      "grad_norm": 0.18056178092956543,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7274,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6430496726992684,
+      "grad_norm": 0.18632574379444122,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.7441,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6469002695417789,
+      "grad_norm": 0.18290062248706818,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7361,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6507508663842896,
+      "grad_norm": 0.18636608123779297,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7315,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6546014632268001,
+      "grad_norm": 0.17545722424983978,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7338,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6584520600693108,
+      "grad_norm": 0.19375012814998627,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7396,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6623026569118213,
+      "grad_norm": 0.19392229616641998,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7333,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6661532537543319,
+      "grad_norm": 0.19220632314682007,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.738,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6700038505968425,
+      "grad_norm": 0.18333011865615845,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7466,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6738544474393531,
+      "grad_norm": 0.17282037436962128,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7414,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6777050442818637,
+      "grad_norm": 0.17782911658287048,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7331,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6815556411243743,
+      "grad_norm": 0.19333240389823914,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.769,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6854062379668848,
+      "grad_norm": 0.17000269889831543,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7451,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6892568348093955,
+      "grad_norm": 0.1862974464893341,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.7615,
+      "step": 1790
+    },
+    {
+      "epoch": 0.693107431651906,
+      "grad_norm": 0.17401714622974396,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7289,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6969580284944167,
+      "grad_norm": 0.18224351108074188,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7227,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7008086253369272,
+      "grad_norm": 0.17548981308937073,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.7455,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7046592221794378,
+      "grad_norm": 0.17890262603759766,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7287,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7085098190219484,
+      "grad_norm": 0.17760072648525238,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7344,
+      "step": 1840
+    },
+    {
+      "epoch": 0.712360415864459,
+      "grad_norm": 0.18590161204338074,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.7485,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7162110127069696,
+      "grad_norm": 0.17566604912281036,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7464,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7200616095494802,
+      "grad_norm": 0.17758487164974213,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7375,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7239122063919907,
+      "grad_norm": 0.1791573017835617,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7482,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7277628032345014,
+      "grad_norm": 0.18236865103244781,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7335,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7316134000770119,
+      "grad_norm": 0.19084496796131134,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7444,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7354639969195226,
+      "grad_norm": 0.17848865687847137,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7417,
+      "step": 1910
+    },
+    {
+      "epoch": 0.7393145937620331,
+      "grad_norm": 0.1804196983575821,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.7311,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7431651906045437,
+      "grad_norm": 0.19530169665813446,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7491,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7470157874470543,
+      "grad_norm": 0.175349622964859,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.7491,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7508663842895649,
+      "grad_norm": 0.181795135140419,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.732,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.19092479348182678,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7568,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7585675779745861,
+      "grad_norm": 0.18209275603294373,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7466,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7624181748170966,
+      "grad_norm": 0.19052787125110626,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7464,
+      "step": 1980
+    },
+    {
+      "epoch": 0.7662687716596073,
+      "grad_norm": 0.19715304672718048,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.7349,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7701193685021178,
+      "grad_norm": 0.17768031358718872,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7355,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7739699653446284,
+      "grad_norm": 0.1720505654811859,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7426,
+      "step": 2010
+    },
+    {
+      "epoch": 0.777820562187139,
+      "grad_norm": 0.17088082432746887,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7229,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7816711590296496,
+      "grad_norm": 0.1799786388874054,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7193,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7855217558721602,
+      "grad_norm": 0.18035617470741272,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.734,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7893723527146708,
+      "grad_norm": 0.17256374657154083,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7369,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7932229495571813,
+      "grad_norm": 0.16417637467384338,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7216,
+      "step": 2060
+    },
+    {
+      "epoch": 0.797073546399692,
+      "grad_norm": 0.19220729172229767,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.7387,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8009241432422025,
+      "grad_norm": 0.1753688007593155,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7145,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8047747400847132,
+      "grad_norm": 0.17328275740146637,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7428,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8086253369272237,
+      "grad_norm": 0.17581234872341156,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.7327,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8124759337697343,
+      "grad_norm": 0.17587591707706451,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7376,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.19289517402648926,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7531,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8201771274547555,
+      "grad_norm": 0.18243718147277832,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.734,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8240277242972661,
+      "grad_norm": 0.17741532623767853,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7361,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8278783211397767,
+      "grad_norm": 0.17963476479053497,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7237,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8317289179822872,
+      "grad_norm": 0.1788288950920105,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7453,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8355795148247979,
+      "grad_norm": 0.18544602394104004,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7394,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8394301116673084,
+      "grad_norm": 0.17030957341194153,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7352,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8432807085098191,
+      "grad_norm": 0.1853291243314743,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.7345,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8471313053523296,
+      "grad_norm": 0.1874118149280548,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7374,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8509819021948402,
+      "grad_norm": 0.172434002161026,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7091,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8548324990373508,
+      "grad_norm": 0.171399787068367,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7422,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586830958798614,
+      "grad_norm": 0.1938866674900055,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7354,
+      "step": 2230
+    },
+    {
+      "epoch": 0.862533692722372,
+      "grad_norm": 0.1717415601015091,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.7467,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663842895648826,
+      "grad_norm": 0.17756830155849457,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7354,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8702348864073931,
+      "grad_norm": 0.21044842898845673,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.717,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740854832499038,
+      "grad_norm": 0.17399075627326965,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7359,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8779360800924143,
+      "grad_norm": 0.16892009973526,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.742,
+      "step": 2280
+    },
+    {
+      "epoch": 0.881786676934925,
+      "grad_norm": 0.18061502277851105,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.7426,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8856372737774355,
+      "grad_norm": 0.17234712839126587,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.7246,
+      "step": 2300
+    },
+    {
+      "epoch": 0.889487870619946,
+      "grad_norm": 0.17435048520565033,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7361,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8933384674624567,
+      "grad_norm": 0.1696014702320099,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7389,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971890643049673,
+      "grad_norm": 0.18293315172195435,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7482,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9010396611474779,
+      "grad_norm": 0.1739678531885147,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7407,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048902579899885,
+      "grad_norm": 0.1825253814458847,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7207,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908740854832499,
+      "grad_norm": 0.1710207760334015,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7355,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125914516750097,
+      "grad_norm": 0.19465436041355133,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7276,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9164420485175202,
+      "grad_norm": 0.17971161007881165,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7403,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202926453600309,
+      "grad_norm": 0.17496006190776825,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7522,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9241432422025414,
+      "grad_norm": 0.19605828821659088,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7453,
+      "step": 2400
+    },
+    {
+      "epoch": 0.927993839045052,
+      "grad_norm": 0.17514467239379883,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7228,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9318444358875626,
+      "grad_norm": 0.17178359627723694,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7528,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9356950327300732,
+      "grad_norm": 0.17764654755592346,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.7462,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9395456295725837,
+      "grad_norm": 0.1758953183889389,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7351,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 0.18783532083034515,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.7236,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9472468232576049,
+      "grad_norm": 0.18793494999408722,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7512,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510974201001156,
+      "grad_norm": 0.18644632399082184,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7463,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9549480169426261,
+      "grad_norm": 0.18042296171188354,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7327,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587986137851366,
+      "grad_norm": 0.1811927706003189,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7337,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9626492106276473,
+      "grad_norm": 0.17384999990463257,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7365,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664998074701578,
+      "grad_norm": 0.16882772743701935,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7352,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9703504043126685,
+      "grad_norm": 0.18615879118442535,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7503,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974201001155179,
+      "grad_norm": 0.17615653574466705,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7291,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9780515979976896,
+      "grad_norm": 0.16925665736198425,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7313,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9819021948402002,
+      "grad_norm": 0.16867858171463013,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7465,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9857527916827108,
+      "grad_norm": 0.16694660484790802,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.73,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9896033885252215,
+      "grad_norm": 0.17222528159618378,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7267,
+      "step": 2570
+    },
+    {
+      "epoch": 0.993453985367732,
+      "grad_norm": 0.16602958738803864,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7173,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9973045822102425,
+      "grad_norm": 0.18533192574977875,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7501,
+      "step": 2590
+    },
+    {
+      "epoch": 1.0,
+      "step": 2597,
+      "total_flos": 7.88903569424751e+18,
+      "train_loss": 0.7546266391270887,
+      "train_runtime": 17359.6778,
+      "train_samples_per_second": 38.302,
+      "train_steps_per_second": 0.15
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 584317136,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.88903569424751e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/smollm2/mc2_h14_378/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb244bb159ca554cb69f33032e48f52fe71d0399f2a788bbdc87374e26649d0f
+size 6264

continuous/smollm2/mc2_h14_378/pretrain/config.json

@@ -0,0 +1,70 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_hidden_size": 1280,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-H-14-worldwide-378",
+  "mm_vision_tower_lr": null,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_h14_378.pt",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_h14_378/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0acf8f477965b8e00e6e6d4d81a6494aec83b2d6ed97fb3de6b3321e93ec6e0f
+size 27281464

continuous/smollm2/mc2_h14_378/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.9178532361984253,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 4.2319,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.08716440200805664,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 3.0251,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.04774459823966026,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 2.8589,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.044527363032102585,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 2.7893,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.06771692633628845,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 2.7567,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.08444875478744507,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 2.7159,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.07662079483270645,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 2.669,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.07086004316806793,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 2.6124,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.07691571861505508,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 2.5642,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.09363417327404022,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 2.5289,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.09424338489770889,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 2.4825,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.07359564304351807,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 2.4499,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.0802946463227272,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 2.4156,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.08112147450447083,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 2.3911,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.09060212969779968,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 2.3815,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.0707947239279747,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 2.3602,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.06782057881355286,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 2.3523,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.07407128810882568,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 2.3356,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.06713297963142395,
+      "learning_rate": 0.000779204504653894,
+      "loss": 2.3265,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.07528743892908096,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 2.299,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.060330286622047424,
+      "learning_rate": 0.00072685988254984,
+      "loss": 2.2926,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.07328024506568909,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 2.2982,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.06756936013698578,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 2.2881,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.05878166854381561,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 2.279,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.06808885186910629,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 2.2722,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.070045106112957,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 2.2757,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.0676538348197937,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 2.2509,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.056227944791316986,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 2.2538,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.06014685332775116,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 2.2388,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.059327803552150726,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 2.2375,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.08105309307575226,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 2.2408,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.05860695615410805,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 2.2399,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.06105547770857811,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 2.2191,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.07350268959999084,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 2.2239,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.07161115854978561,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 2.2211,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.06479869782924652,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 2.2222,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.06047327071428299,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 2.212,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.059599753469228745,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 2.2173,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.06190260127186775,
+      "learning_rate": 0.000208323983828828,
+      "loss": 2.2034,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.059812091290950775,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 2.2022,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.058945804834365845,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 2.2023,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.06149464100599289,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 2.1933,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.05788726359605789,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 2.1937,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.061576977372169495,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 2.201,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.060316119343042374,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 2.1922,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.05890503525733948,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 2.1826,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.05617895722389221,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 2.1797,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.054710328578948975,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 2.1833,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.05589200183749199,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 2.1881,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.054967813193798065,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 2.1924,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.05568827688694,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 2.1812,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.05569489300251007,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 2.1758,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.05549915134906769,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 2.1804,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.056265540421009064,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 2.1806,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 4.490378185266954e+17,
+      "train_loss": 2.3699013001328213,
+      "train_runtime": 3975.5244,
+      "train_samples_per_second": 140.391,
+      "train_steps_per_second": 0.137
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 33258880,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.490378185266954e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/smollm2/mc2_l14_224/finetune/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

continuous/smollm2/mc2_l14_224/finetune/config.json

@@ -0,0 +1,70 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_hidden_size": 1024,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-L-14",
+  "mm_vision_tower_lr": null,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_l14_224.pt",
+  "vocab_size": 49152
+}

continuous/smollm2/mc2_l14_224/finetune/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.57.6"
+}