| { |
| "args": { |
| "task_file": "scripts/fallacies.json", |
| "dataset": null, |
| "dataset_revision": null, |
| "split": "train", |
| "text_column": null, |
| "label_column": null, |
| "model_dir": null, |
| "base_revision": "1c5edc17a7acd8701df6fc341c0d179f1c62c982", |
| "output_dir": "./tmp/stage1", |
| "device": "auto", |
| "amp": false, |
| "epochs": 4, |
| "micro_batch": 8, |
| "grad_accum": 4, |
| "group_size": 4, |
| "lr_encoder": 2.5e-05, |
| "lr_head": 0.0001, |
| "weight_decay": 0.01, |
| "sigma_start": 0.4, |
| "sigma_end": 0.1, |
| "seed": 42, |
| "max_items": 0, |
| "calib_max": 400, |
| "val_frac": 0.1, |
| "negative_file": "/Users/brian/git/receptron/laya/scripts/negatives.jsonl", |
| "extra_file": "none", |
| "dry_run": false, |
| "dry_steps": 5, |
| "finalize_only": false |
| }, |
| "base_model": "convaiinnovations/laya", |
| "base_revision": "1c5edc17a7acd8701df6fc341c0d179f1c62c982", |
| "base_model_dir": "/Users/brian/.cache/huggingface/hub/models--convaiinnovations--laya/snapshots/1c5edc17a7acd8701df6fc341c0d179f1c62c982", |
| "dataset": "tasksource/logical-fallacy", |
| "dataset_revision": "37e9b0537a86e72e9eaf6ee8c9a27d872a944103", |
| "env": { |
| "laya": "0.3.5", |
| "torch": "2.14.0", |
| "transformers": "5.17.0", |
| "datasets": "5.0.1", |
| "safetensors": "0.8.0", |
| "numpy": "2.5.3" |
| }, |
| "epochs": [ |
| { |
| "epoch": 1, |
| "avg_loss": 1.9571953387693926 |
| }, |
| { |
| "epoch": 2, |
| "avg_loss": 1.4149250892075624 |
| }, |
| { |
| "epoch": 3, |
| "avg_loss": 0.9954640326174823 |
| }, |
| { |
| "epoch": 4, |
| "avg_loss": 0.7398663367737424 |
| } |
| ], |
| "fitted_temperatures": [ |
| 1.8769, |
| 1.2, |
| 1.2 |
| ], |
| "val": { |
| "accuracy": 0.654320987654321, |
| "mean_argmax_confidence": 0.7798909438858307, |
| "n": 243 |
| }, |
| "test": { |
| "accuracy": 0.5048923679060665, |
| "mean_argmax_confidence": 0.6494024801860817, |
| "n": 511 |
| }, |
| "train_items": 2196, |
| "device": "mps", |
| "amp": false |
| } |
