| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03854307188282906, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007708614376565812, | |
| "eval_loss": 6.92765474319458, | |
| "eval_runtime": 10.9768, | |
| "eval_samples_per_second": 49.832, | |
| "eval_steps_per_second": 24.962, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003854307188282906, | |
| "grad_norm": 0.2718292474746704, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9326, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007708614376565812, | |
| "grad_norm": 0.28688400983810425, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9263, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007708614376565812, | |
| "eval_loss": 6.924817085266113, | |
| "eval_runtime": 10.2915, | |
| "eval_samples_per_second": 53.151, | |
| "eval_steps_per_second": 26.624, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011562921564848718, | |
| "grad_norm": 0.2759840488433838, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9246, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015417228753131625, | |
| "grad_norm": 0.2750642001628876, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.9265, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015417228753131625, | |
| "eval_loss": 6.918467044830322, | |
| "eval_runtime": 10.2873, | |
| "eval_samples_per_second": 53.172, | |
| "eval_steps_per_second": 26.635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01927153594141453, | |
| "grad_norm": 0.313626229763031, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.9111, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023125843129697437, | |
| "grad_norm": 0.28255218267440796, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9186, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023125843129697437, | |
| "eval_loss": 6.913368225097656, | |
| "eval_runtime": 10.2762, | |
| "eval_samples_per_second": 53.23, | |
| "eval_steps_per_second": 26.664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02698015031798034, | |
| "grad_norm": 0.29919466376304626, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.9124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03083445750626325, | |
| "grad_norm": 0.27636855840682983, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.9174, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03083445750626325, | |
| "eval_loss": 6.910731792449951, | |
| "eval_runtime": 10.2698, | |
| "eval_samples_per_second": 53.263, | |
| "eval_steps_per_second": 26.68, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.034688764694546154, | |
| "grad_norm": 0.29338952898979187, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.9162, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03854307188282906, | |
| "grad_norm": 0.3097763955593109, | |
| "learning_rate": 0.0, | |
| "loss": 6.9151, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03854307188282906, | |
| "eval_loss": 6.910257339477539, | |
| "eval_runtime": 9.4458, | |
| "eval_samples_per_second": 57.909, | |
| "eval_steps_per_second": 29.008, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 131833036800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |