| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2679738562091503, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.33201581027667987, | |
| "eval_f1_sklearn": 0.9443381865022052, | |
| "eval_loss": 0.13136763870716095, | |
| "eval_precision": 0.4140845070422535, | |
| "eval_precision_sklearn": 0.9443381865022054, | |
| "eval_recall": 0.2770970782280867, | |
| "eval_recall_sklearn": 0.9443381865022054, | |
| "eval_runtime": 4.8663, | |
| "eval_samples_per_second": 83.842, | |
| "eval_steps_per_second": 20.961, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.5698051948051949, | |
| "eval_f1_sklearn": 0.9491393106678637, | |
| "eval_loss": 0.1262897104024887, | |
| "eval_precision": 0.5003563791874555, | |
| "eval_precision_sklearn": 0.9491393106678637, | |
| "eval_recall": 0.6616399622997172, | |
| "eval_recall_sklearn": 0.9491393106678637, | |
| "eval_runtime": 5.0825, | |
| "eval_samples_per_second": 80.275, | |
| "eval_steps_per_second": 20.069, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.6133108677337826, | |
| "eval_f1_sklearn": 0.954721105429564, | |
| "eval_loss": 0.14351697266101837, | |
| "eval_precision": 0.5544554455445545, | |
| "eval_precision_sklearn": 0.954721105429564, | |
| "eval_recall": 0.6861451460885957, | |
| "eval_recall_sklearn": 0.954721105429564, | |
| "eval_runtime": 5.0462, | |
| "eval_samples_per_second": 80.853, | |
| "eval_steps_per_second": 20.213, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 3.2679738562091503, | |
| "grad_norm": 0.41928789019584656, | |
| "learning_rate": 2.2045914347950052e-05, | |
| "loss": 0.0672, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 765, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 433135952304768.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "learning_rate": 6.364197915540298e-05, | |
| "metric": "eval/loss", | |
| "per_device_train_batch_size": 8 | |
| } | |
| } | |