| { | |
| "best_global_step": 220, | |
| "best_metric": 0.9837687666378767, | |
| "best_model_checkpoint": "intent_classifier_v2/checkpoint-220", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 1.5899983644485474, | |
| "learning_rate": 1.9600000000000003e-06, | |
| "loss": 2.5642, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.1881720430107527, | |
| "eval_f1": 0.10086428092694365, | |
| "eval_loss": 2.5428154468536377, | |
| "eval_precision": 0.0936228251427814, | |
| "eval_recall": 0.1881720430107527, | |
| "eval_runtime": 0.1839, | |
| "eval_samples_per_second": 1011.503, | |
| "eval_steps_per_second": 65.258, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 3.272284984588623, | |
| "learning_rate": 3.96e-06, | |
| "loss": 2.5118, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.26344086021505375, | |
| "eval_f1": 0.17357707395658062, | |
| "eval_loss": 2.3705923557281494, | |
| "eval_precision": 0.23162059134445975, | |
| "eval_recall": 0.26344086021505375, | |
| "eval_runtime": 0.202, | |
| "eval_samples_per_second": 920.577, | |
| "eval_steps_per_second": 59.392, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 4.249340057373047, | |
| "learning_rate": 5.9600000000000005e-06, | |
| "loss": 2.303, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8064516129032258, | |
| "eval_f1": 0.7699332427341867, | |
| "eval_loss": 1.9005680084228516, | |
| "eval_precision": 0.8112076095947064, | |
| "eval_recall": 0.8064516129032258, | |
| "eval_runtime": 0.18, | |
| "eval_samples_per_second": 1033.189, | |
| "eval_steps_per_second": 66.657, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 4.2065110206604, | |
| "learning_rate": 7.960000000000002e-06, | |
| "loss": 1.8712, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9838709677419355, | |
| "eval_f1": 0.9837687666378767, | |
| "eval_loss": 1.1924996376037598, | |
| "eval_precision": 0.984740928604229, | |
| "eval_recall": 0.9838709677419355, | |
| "eval_runtime": 0.1796, | |
| "eval_samples_per_second": 1035.622, | |
| "eval_steps_per_second": 66.814, | |
| "step": 220 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 275, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 27852593715744.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |