Text Classification
Laya
Safetensors
English
ledgar
lexglue
legal
contracts
calibrated
selective-prediction
Eval Results (legacy)
Instructions to use VibeHash/laya-ledgar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use VibeHash/laya-ledgar with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download train.json from VibeHash/laya-ledgar: direct link, hf CLI and curl.
- Browser
- Download file 5.11 kB
-
https://huggingface.co/VibeHash/laya-ledgar/resolve/main/train.json
- Command line
-
hf download hf://VibeHash/laya-ledgar/train.json
-
curl -L -o train.json https://huggingface.co/VibeHash/laya-ledgar/resolve/main/train.json
5.11 kB
| { | |
| "task": "ledgar", | |
| "name": "ce-seed0", | |
| "seed": 0, | |
| "seconds": 25980.469927399987, | |
| "dev": { | |
| "rows": 2000, | |
| "seed": 20261118, | |
| "train_rows": 57934, | |
| "dropped_same_text": 66 | |
| }, | |
| "base": { | |
| "repo": "convaiinnovations/laya", | |
| "revision": "85cc74ddae6109077ebe2853a9b3077fb6606a78", | |
| "weights_sha256": "891102d372688fc2a094dac56a384bc537b87c63f21f9f3dac0be2b7cbc8d86c" | |
| }, | |
| "config": { | |
| "epochs": 4, | |
| "micro_batch": 8, | |
| "grad_accum": 8, | |
| "encoder_lr": 2.5e-05, | |
| "head_lr": 0.0001, | |
| "min_lr": 1e-06, | |
| "weight_decay": 0.01, | |
| "grad_clip": 1.0, | |
| "loss": "soft-ce", | |
| "rl_samples": 4, | |
| "sigma_start": 0.4, | |
| "sigma_end": 0.1, | |
| "w_sph": 0.75, | |
| "w_rps": 1.0, | |
| "shuffle_options": [], | |
| "option_layout": null, | |
| "freeze_encoder": false, | |
| "calib_max": 400, | |
| "calib_frac": 0.1, | |
| "calib_seed": 20260922, | |
| "seed": 0, | |
| "max_len": 768, | |
| "head_max_len": 512, | |
| "amp": null, | |
| "gradient_checkpointing": null, | |
| "log_every": 100, | |
| "label_smoothing": 0.0, | |
| "text_column": "text", | |
| "label_column": "label", | |
| "question_id": "label", | |
| "instructions": null, | |
| "eval_data": null, | |
| "target_error": 0.01, | |
| "min_abstain_n": 10 | |
| }, | |
| "summary": { | |
| "train_items": 57534, | |
| "calibration_items": 400, | |
| "eval_items": 400, | |
| "skipped": {}, | |
| "epoch_loss": [ | |
| 0.6323961586747381, | |
| 0.32258454987853263, | |
| 0.1312420500772953, | |
| 0.04140990528605578 | |
| ], | |
| "temperature": [ | |
| 1.9877519607543945, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "temperature_by_options": {}, | |
| "n_by_bucket": { | |
| "choice:11+": 400 | |
| }, | |
| "calibration": { | |
| "choice": { | |
| "items": 400, | |
| "temperature": 1.9877519607543945, | |
| "issues": [], | |
| "accuracy": 0.8575, | |
| "mean_confidence": 0.8994799126217312 | |
| }, | |
| "score": { | |
| "items": 0, | |
| "temperature": 1.0, | |
| "issues": [] | |
| }, | |
| "noul": { | |
| "items": 0, | |
| "temperature": 1.0, | |
| "issues": [] | |
| } | |
| }, | |
| "abstention_thresholds": { | |
| "choice:11+": 1.0 | |
| }, | |
| "train_report": { | |
| "eval_source": "calibration_slice", | |
| "eval_mode": "in_sample_calibration", | |
| "is_held_out": false, | |
| "eval_items": 400, | |
| "note": "Metrics reflect in-sample calibration fit, not independent held-out evaluation. Provide --eval for held-out validation.", | |
| "before": { | |
| "items": 400, | |
| "loss": 23.8939, | |
| "accuracy": 0.3875, | |
| "mean_confidence": 0.9603, | |
| "ece": 0.5728, | |
| "brier": 1.1697, | |
| "brier_top1": 0.5598, | |
| "by_type": { | |
| "choice": { | |
| "items": 400, | |
| "loss": 23.8939, | |
| "accuracy": 0.3875, | |
| "mean_confidence": 0.9603, | |
| "ece": 0.5728, | |
| "brier": 1.1697, | |
| "brier_top1": 0.5598 | |
| } | |
| } | |
| }, | |
| "after": { | |
| "items": 400, | |
| "loss": 0.496, | |
| "accuracy": 0.8575, | |
| "mean_confidence": 0.8995, | |
| "ece": 0.0657, | |
| "brier": 0.2175, | |
| "brier_top1": 0.0981, | |
| "by_type": { | |
| "choice": { | |
| "items": 400, | |
| "loss": 0.496, | |
| "accuracy": 0.8575, | |
| "mean_confidence": 0.8995, | |
| "ece": 0.0657, | |
| "brier": 0.2175, | |
| "brier_top1": 0.0981 | |
| } | |
| } | |
| }, | |
| "comparison": { | |
| "delta_accuracy": 0.47, | |
| "delta_loss": -23.3979, | |
| "delta_ece": -0.5071, | |
| "delta_brier": -0.9522, | |
| "delta_brier_top1": -0.4617, | |
| "delta_mean_confidence": -0.0608 | |
| }, | |
| "calibration": { | |
| "choice": { | |
| "items": 400, | |
| "temperature": 1.9877519607543945, | |
| "issues": [], | |
| "accuracy": 0.8575, | |
| "mean_confidence": 0.8994799126217312 | |
| }, | |
| "score": { | |
| "items": 0, | |
| "temperature": 1.0, | |
| "issues": [] | |
| }, | |
| "noul": { | |
| "items": 0, | |
| "temperature": 1.0, | |
| "issues": [] | |
| } | |
| }, | |
| "abstention_thresholds": { | |
| "choice:11+": 1.0 | |
| }, | |
| "training": { | |
| "epochs": 4, | |
| "micro_batch": 8, | |
| "grad_accum": 8, | |
| "encoder_lr": 2.5e-05, | |
| "head_lr": 0.0001, | |
| "min_lr": 1e-06, | |
| "weight_decay": 0.01, | |
| "grad_clip": 1.0, | |
| "loss": "soft-ce", | |
| "rl_samples": 4, | |
| "sigma_start": 0.4, | |
| "sigma_end": 0.1, | |
| "w_sph": 0.75, | |
| "w_rps": 1.0, | |
| "shuffle_options": [], | |
| "option_layout": null, | |
| "freeze_encoder": false, | |
| "calib_max": 400, | |
| "calib_frac": 0.1, | |
| "calib_seed": 20260922, | |
| "seed": 0, | |
| "max_len": 768, | |
| "head_max_len": 512, | |
| "amp": null, | |
| "gradient_checkpointing": null, | |
| "log_every": 100, | |
| "label_smoothing": 0.0, | |
| "text_column": "text", | |
| "label_column": "label", | |
| "question_id": "label", | |
| "instructions": null, | |
| "eval_data": null, | |
| "target_error": 0.01, | |
| "min_abstain_n": 10 | |
| } | |
| } | |
| } | |
| } | |