| { | |
| "best_metric": 0.8379377126693726, | |
| "best_model_checkpoint": "autotrain-pe4xw-rb8r8/checkpoint-126", | |
| "epoch": 2.9411764705882355, | |
| "eval_steps": 500, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 20.175811767578125, | |
| "learning_rate": 2.893805309734513e-05, | |
| "loss": 0.5842, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 13.500060081481934, | |
| "learning_rate": 2.442477876106195e-05, | |
| "loss": 0.4413, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cosine_accuracy": 0.9651162790697675, | |
| "eval_loss": 0.8393570780754089, | |
| "eval_runtime": 77.8013, | |
| "eval_samples_per_second": 1.105, | |
| "eval_steps_per_second": 0.141, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.188235294117647, | |
| "grad_norm": 14.887923240661621, | |
| "learning_rate": 1.991150442477876e-05, | |
| "loss": 0.4844, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.5882352941176472, | |
| "grad_norm": 21.601289749145508, | |
| "learning_rate": 1.5398230088495576e-05, | |
| "loss": 0.4827, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.988235294117647, | |
| "grad_norm": 19.94289207458496, | |
| "learning_rate": 1.088495575221239e-05, | |
| "loss": 0.5319, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_cosine_accuracy": 0.9651162790697675, | |
| "eval_loss": 0.8382742404937744, | |
| "eval_runtime": 78.3331, | |
| "eval_samples_per_second": 1.098, | |
| "eval_steps_per_second": 0.14, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.376470588235294, | |
| "grad_norm": 36.912296295166016, | |
| "learning_rate": 6.371681415929204e-06, | |
| "loss": 0.5825, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.776470588235294, | |
| "grad_norm": 15.572786331176758, | |
| "learning_rate": 1.8584070796460177e-06, | |
| "loss": 0.5355, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "eval_cosine_accuracy": 0.9651162790697675, | |
| "eval_loss": 0.8379377126693726, | |
| "eval_runtime": 77.9595, | |
| "eval_samples_per_second": 1.103, | |
| "eval_steps_per_second": 0.141, | |
| "step": 126 | |
| } | |
| ], | |
| "logging_steps": 17, | |
| "max_steps": 126, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |