| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00013361793954456326, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.3361793954456326e-05, | |
| "grad_norm": 14.365166664123535, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.3361793954456326e-05, | |
| "eval_loss": 2.254793405532837, | |
| "eval_runtime": 550.269, | |
| "eval_samples_per_second": 57.267, | |
| "eval_steps_per_second": 28.633, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.6723587908912652e-05, | |
| "grad_norm": 18.047311782836914, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9175, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.0085381863368976e-05, | |
| "grad_norm": 15.776288986206055, | |
| "learning_rate": 6e-05, | |
| "loss": 2.073, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0085381863368976e-05, | |
| "eval_loss": 2.17337965965271, | |
| "eval_runtime": 548.3902, | |
| "eval_samples_per_second": 57.463, | |
| "eval_steps_per_second": 28.731, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.3447175817825303e-05, | |
| "grad_norm": 10.586884498596191, | |
| "learning_rate": 8e-05, | |
| "loss": 1.764, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 6.680896977228163e-05, | |
| "grad_norm": 10.577876091003418, | |
| "learning_rate": 0.0001, | |
| "loss": 2.277, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.017076372673795e-05, | |
| "grad_norm": 6.899762153625488, | |
| "learning_rate": 0.00012, | |
| "loss": 1.545, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 8.017076372673795e-05, | |
| "eval_loss": 1.648829698562622, | |
| "eval_runtime": 547.9706, | |
| "eval_samples_per_second": 57.507, | |
| "eval_steps_per_second": 28.753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.353255768119427e-05, | |
| "grad_norm": 19.941368103027344, | |
| "learning_rate": 0.00014, | |
| "loss": 1.844, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00010689435163565061, | |
| "grad_norm": 35.24299621582031, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4162, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00012025614559010693, | |
| "grad_norm": 42.267860412597656, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3721, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00012025614559010693, | |
| "eval_loss": 1.2308964729309082, | |
| "eval_runtime": 550.5591, | |
| "eval_samples_per_second": 57.236, | |
| "eval_steps_per_second": 28.618, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00013361793954456326, | |
| "grad_norm": 12.464423179626465, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3618, | |
| "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": 255791978250240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |