| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001894692965005021, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.894692965005021e-05, | |
| "grad_norm": 0.5176880359649658, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2283, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.894692965005021e-05, | |
| "eval_loss": 0.1918485462665558, | |
| "eval_runtime": 771.5976, | |
| "eval_samples_per_second": 28.801, | |
| "eval_steps_per_second": 14.401, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.789385930010042e-05, | |
| "grad_norm": 0.25180771946907043, | |
| "learning_rate": 4e-05, | |
| "loss": 0.132, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.684078895015063e-05, | |
| "grad_norm": 0.40558627247810364, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1823, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.684078895015063e-05, | |
| "eval_loss": 0.18599580228328705, | |
| "eval_runtime": 773.4066, | |
| "eval_samples_per_second": 28.734, | |
| "eval_steps_per_second": 14.368, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.578771860020084e-05, | |
| "grad_norm": 0.3714902698993683, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1652, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 9.473464825025105e-05, | |
| "grad_norm": 0.3826047480106354, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1596, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011368157790030126, | |
| "grad_norm": 0.3728172183036804, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011368157790030126, | |
| "eval_loss": 0.11260570585727692, | |
| "eval_runtime": 773.7308, | |
| "eval_samples_per_second": 28.722, | |
| "eval_steps_per_second": 14.362, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013262850755035147, | |
| "grad_norm": 0.33123376965522766, | |
| "learning_rate": 0.00014, | |
| "loss": 0.091, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00015157543720040168, | |
| "grad_norm": 0.26363614201545715, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001705223668504519, | |
| "grad_norm": 0.21541348099708557, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0581, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001705223668504519, | |
| "eval_loss": 0.052274443209171295, | |
| "eval_runtime": 775.7825, | |
| "eval_samples_per_second": 28.646, | |
| "eval_steps_per_second": 14.324, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001894692965005021, | |
| "grad_norm": 0.3085590898990631, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0466, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 862667895472128.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |