Text Classification
Transformers
Safetensors
Russian
customer-support
hierarchical-classification
mps
minilm
Instructions to use ZenMan67/support-ticket-classifiers-minilm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZenMan67/support-ticket-classifiers-minilm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ZenMan67/support-ticket-classifiers-minilm")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ZenMan67/support-ticket-classifiers-minilm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download human/metrics.json from ZenMan67/support-ticket-classifiers-minilm: direct link, hf CLI and curl.
- Browser
- Download file 3.02 kB
-
https://huggingface.co/ZenMan67/support-ticket-classifiers-minilm/resolve/main/human/metrics.json
- Command line
-
hf download hf://ZenMan67/support-ticket-classifiers-minilm/human/metrics.json
-
curl -L -o metrics.json https://huggingface.co/ZenMan67/support-ticket-classifiers-minilm/resolve/main/human/metrics.json
3.02 kB
| { | |
| "task": "human", | |
| "best_epoch": 6, | |
| "training_seconds": 111.95542904100148, | |
| "split_sizes": { | |
| "train": 880, | |
| "validation": 110, | |
| "test": 110 | |
| }, | |
| "validation": { | |
| "loss": 1.267178336056796, | |
| "accuracy": 0.8363636363636363, | |
| "macro_f1": 0.7900596877869606 | |
| }, | |
| "test": { | |
| "loss": 1.4121767195788297, | |
| "accuracy": 0.7454545454545455, | |
| "macro_f1": 0.6897269397269397 | |
| }, | |
| "test_confusions": [ | |
| { | |
| "gold": "multi_intent_with_financial_risk", | |
| "predicted": "refund_missing_after_deadline", | |
| "count": 5 | |
| }, | |
| { | |
| "gold": "account_takeover", | |
| "predicted": "personal_data_or_payment_card_exposed", | |
| "count": 5 | |
| }, | |
| { | |
| "gold": "order_marked_delivered_but_not_received", | |
| "predicted": "multi_intent_with_financial_risk", | |
| "count": 5 | |
| }, | |
| { | |
| "gold": "change_delivery_address_after_dispatch", | |
| "predicted": "cancel_order_after_dispatch", | |
| "count": 5 | |
| }, | |
| { | |
| "gold": "fraud_or_phishing", | |
| "predicted": "account_takeover", | |
| "count": 3 | |
| }, | |
| { | |
| "gold": "missing_item_in_delivered_order", | |
| "predicted": "refund_amount_dispute", | |
| "count": 3 | |
| }, | |
| { | |
| "gold": "fraud_or_phishing", | |
| "predicted": "privacy_data_deletion_request", | |
| "count": 2 | |
| } | |
| ], | |
| "history": [ | |
| { | |
| "epoch": 1, | |
| "train_loss": 3.0446458036249333, | |
| "validation_loss": 2.9481882918964732, | |
| "validation_accuracy": 0.3181818181818182, | |
| "validation_macro_f1": 0.275695272469466 | |
| }, | |
| { | |
| "epoch": 2, | |
| "train_loss": 2.5696960145776924, | |
| "validation_loss": 2.4496376210992987, | |
| "validation_accuracy": 0.5818181818181818, | |
| "validation_macro_f1": 0.5069444444444445 | |
| }, | |
| { | |
| "epoch": 3, | |
| "train_loss": 1.8286097873340954, | |
| "validation_loss": 1.8624537467956543, | |
| "validation_accuracy": 0.7909090909090909, | |
| "validation_macro_f1": 0.7550946528219256 | |
| }, | |
| { | |
| "epoch": 4, | |
| "train_loss": 1.237558323686773, | |
| "validation_loss": 1.5112867398695513, | |
| "validation_accuracy": 0.8, | |
| "validation_macro_f1": 0.7386363636363636 | |
| }, | |
| { | |
| "epoch": 5, | |
| "train_loss": 0.899948058345101, | |
| "validation_loss": 1.34841853055087, | |
| "validation_accuracy": 0.8272727272727273, | |
| "validation_macro_f1": 0.7803030303030304 | |
| }, | |
| { | |
| "epoch": 6, | |
| "train_loss": 0.7283082962036133, | |
| "validation_loss": 1.267178336056796, | |
| "validation_accuracy": 0.8363636363636363, | |
| "validation_macro_f1": 0.7900596877869606 | |
| }, | |
| { | |
| "epoch": 7, | |
| "train_loss": 0.6527352463115346, | |
| "validation_loss": 1.2407976128838278, | |
| "validation_accuracy": 0.8090909090909091, | |
| "validation_macro_f1": 0.7660697887970614 | |
| }, | |
| { | |
| "epoch": 8, | |
| "train_loss": 0.6315497528422963, | |
| "validation_loss": 1.2309001250700518, | |
| "validation_accuracy": 0.8181818181818182, | |
| "validation_macro_f1": 0.7732847960120687 | |
| } | |
| ] | |
| } | |