| { | |
| "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": 0.0, | |
| "eval_f1_sklearn": 0.938717358210703, | |
| "eval_loss": 0.24921800196170807, | |
| "eval_precision": 0.0, | |
| "eval_precision_sklearn": 0.938717358210703, | |
| "eval_recall": 0.0, | |
| "eval_recall_sklearn": 0.938717358210703, | |
| "eval_runtime": 4.264, | |
| "eval_samples_per_second": 95.684, | |
| "eval_steps_per_second": 23.921, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.0, | |
| "eval_f1_sklearn": 0.938717358210703, | |
| "eval_loss": 0.21044552326202393, | |
| "eval_precision": 0.0, | |
| "eval_precision_sklearn": 0.938717358210703, | |
| "eval_recall": 0.0, | |
| "eval_recall_sklearn": 0.938717358210703, | |
| "eval_runtime": 4.3149, | |
| "eval_samples_per_second": 94.557, | |
| "eval_steps_per_second": 23.639, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.0, | |
| "eval_f1_sklearn": 0.938717358210703, | |
| "eval_loss": 0.19400592148303986, | |
| "eval_precision": 0.0, | |
| "eval_precision_sklearn": 0.938717358210703, | |
| "eval_recall": 0.0, | |
| "eval_recall_sklearn": 0.938717358210703, | |
| "eval_runtime": 4.2786, | |
| "eval_samples_per_second": 95.358, | |
| "eval_steps_per_second": 23.839, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 3.2679738562091503, | |
| "grad_norm": 1.0329492092132568, | |
| "learning_rate": 3.464052287581699e-07, | |
| "loss": 0.3032, | |
| "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": 1e-06, | |
| "metric": "eval/loss", | |
| "per_device_train_batch_size": 8 | |
| } | |
| } | |