| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010265359544218037, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020530719088436073, | |
| "eval_loss": 1.3546793460845947, | |
| "eval_runtime": 87.8517, | |
| "eval_samples_per_second": 23.346, | |
| "eval_steps_per_second": 11.679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002053071908843607, | |
| "grad_norm": 1.1122969388961792, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004106143817687214, | |
| "grad_norm": 0.7866343259811401, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.5164, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006159215726530822, | |
| "grad_norm": 0.9349194765090942, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.3543, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008212287635374429, | |
| "grad_norm": 0.6453638076782227, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.3246, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010265359544218037, | |
| "grad_norm": 0.4768398702144623, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.3237, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010265359544218037, | |
| "eval_loss": 0.3221627175807953, | |
| "eval_runtime": 86.3643, | |
| "eval_samples_per_second": 23.748, | |
| "eval_steps_per_second": 11.88, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.140578662219776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |