| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.901960784313726, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "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": 0.9551506074222, | |
| "eval_loss": 0.19100283086299896, | |
| "eval_precision": 0.0, | |
| "eval_precision_sklearn": 0.9551506074222, | |
| "eval_recall": 0.0, | |
| "eval_recall_sklearn": 0.9551506074222, | |
| "eval_runtime": 4.3455, | |
| "eval_samples_per_second": 93.89, | |
| "eval_steps_per_second": 23.472, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.6339869281045751, | |
| "grad_norm": 1.0916732549667358, | |
| "learning_rate": 6.73202614379085e-07, | |
| "loss": 0.3505, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.0, | |
| "eval_f1_sklearn": 0.9551506074222, | |
| "eval_loss": 0.17071670293807983, | |
| "eval_precision": 0.0, | |
| "eval_precision_sklearn": 0.9551506074222, | |
| "eval_recall": 0.0, | |
| "eval_recall_sklearn": 0.9551506074222, | |
| "eval_runtime": 4.8134, | |
| "eval_samples_per_second": 84.764, | |
| "eval_steps_per_second": 21.191, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.0, | |
| "eval_f1_sklearn": 0.9551506074222, | |
| "eval_loss": 0.15558268129825592, | |
| "eval_precision": 0.0, | |
| "eval_precision_sklearn": 0.9551506074222, | |
| "eval_recall": 0.0, | |
| "eval_recall_sklearn": 0.9551506074222, | |
| "eval_runtime": 4.3951, | |
| "eval_samples_per_second": 92.83, | |
| "eval_steps_per_second": 23.208, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 3.2679738562091503, | |
| "grad_norm": 1.2043535709381104, | |
| "learning_rate": 3.464052287581699e-07, | |
| "loss": 0.1655, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.0, | |
| "eval_f1_sklearn": 0.9551506074222, | |
| "eval_loss": 0.1459077149629593, | |
| "eval_precision": 0.0, | |
| "eval_precision_sklearn": 0.9551506074222, | |
| "eval_recall": 0.0, | |
| "eval_recall_sklearn": 0.9551506074222, | |
| "eval_runtime": 5.1168, | |
| "eval_samples_per_second": 79.737, | |
| "eval_steps_per_second": 19.934, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 4.901960784313726, | |
| "grad_norm": 3.849971294403076, | |
| "learning_rate": 1.9607843137254902e-08, | |
| "loss": 0.1449, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1530, | |
| "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": 454778868404304.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "learning_rate": 1e-06, | |
| "metric": "eval/loss", | |
| "per_device_train_batch_size": 4 | |
| } | |
| } | |