| { |
| "stage": 4, |
| "dataset_id": "THemidli/applied-ner-stage4-improved", |
| "base_model": "google/bert_uncased_L-2_H-128_A-2", |
| "seed": 20260802, |
| "labels": [ |
| "O", |
| "B-PERSON", |
| "I-PERSON", |
| "B-ORGANIZATION", |
| "I-ORGANIZATION", |
| "B-LOCATION", |
| "I-LOCATION", |
| "B-TIMEDATE", |
| "I-TIMEDATE", |
| "B-PRODUCT", |
| "I-PRODUCT", |
| "B-WORKOFART", |
| "I-WORKOFART", |
| "B-JOB", |
| "I-JOB", |
| "B-AMOUNT", |
| "I-AMOUNT" |
| ], |
| "parameter_count": 4371601, |
| "trainable_parameter_count": 4371601, |
| "device": "mps", |
| "platform": "macOS-27.0-arm64-arm-64bit", |
| "torch_version": "2.13.0", |
| "train_records": 841, |
| "test_records": 159, |
| "train_chunks": 865, |
| "test_chunks": 165, |
| "max_length": 256, |
| "wall_seconds": 14.937, |
| "trainer_metrics": { |
| "train_runtime": 14.8851, |
| "train_samples_per_second": 929.789, |
| "train_steps_per_second": 30.097, |
| "total_flos": 6246600094602.0, |
| "train_loss": 0.4432598276595984, |
| "epoch": 16.0 |
| }, |
| "hyperparameters": { |
| "epochs": 16, |
| "learning_rate": 0.0005, |
| "train_batch_size": 32, |
| "eval_batch_size": 64, |
| "weight_decay": 0.02, |
| "label_smoothing_factor": 0.0, |
| "warmup_steps": 45, |
| "scheduler": "linear", |
| "hidden_dropout": 0.1, |
| "attention_dropout": 0.1, |
| "classifier_dropout": 0.1 |
| }, |
| "train_overall": { |
| "overall_precision": 0.9539951573849879, |
| "overall_recall": 0.9708781362007168, |
| "overall_f1": 0.9623626068613301, |
| "overall_accuracy": 0.9948478767829058 |
| }, |
| "test_overall": { |
| "overall_precision": 0.42610652663165793, |
| "overall_recall": 0.5264133456904542, |
| "overall_f1": 0.4709784411276949, |
| "overall_accuracy": 0.8332408742926883 |
| }, |
| "test_f1_change_vs_stage3": 0.002472883284961258 |
| } |
|
|
