| { | |
| "best_metric": 0.3349315822124481, | |
| "best_model_checkpoint": "model/checkpoint-13230", | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 13230, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9415076375007629, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.3384, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.17596371882086168, | |
| "eval_f1": 0.05266017963940943, | |
| "eval_loss": 0.33717620372772217, | |
| "eval_precision": 0.030963230341267273, | |
| "eval_recall": 0.17596371882086168, | |
| "eval_runtime": 129.9657, | |
| "eval_samples_per_second": 33.932, | |
| "eval_steps_per_second": 4.247, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.411308765411377, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3376, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.17596371882086168, | |
| "eval_f1": 0.05266017963940943, | |
| "eval_loss": 0.33663079142570496, | |
| "eval_precision": 0.030963230341267273, | |
| "eval_recall": 0.17596371882086168, | |
| "eval_runtime": 129.7235, | |
| "eval_samples_per_second": 33.995, | |
| "eval_steps_per_second": 4.255, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.9971898198127747, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.3363, | |
| "step": 13230 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.17596371882086168, | |
| "eval_f1": 0.05266017963940943, | |
| "eval_loss": 0.3349315822124481, | |
| "eval_precision": 0.030963230341267273, | |
| "eval_recall": 0.17596371882086168, | |
| "eval_runtime": 129.7239, | |
| "eval_samples_per_second": 33.995, | |
| "eval_steps_per_second": 4.255, | |
| "step": 13230 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 44100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "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": 9.863794837757952e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |