| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02897291032884253, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005794582065768506, | |
| "eval_loss": 1.5164941549301147, | |
| "eval_runtime": 50.5347, | |
| "eval_samples_per_second": 14.386, | |
| "eval_steps_per_second": 7.203, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028972910328842532, | |
| "grad_norm": 1.2197678089141846, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5117, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0057945820657685065, | |
| "grad_norm": 1.9201555252075195, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2836, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0057945820657685065, | |
| "eval_loss": 1.1375128030776978, | |
| "eval_runtime": 50.8842, | |
| "eval_samples_per_second": 14.287, | |
| "eval_steps_per_second": 7.153, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008691873098652759, | |
| "grad_norm": 1.7174865007400513, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8639, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011589164131537013, | |
| "grad_norm": 1.550424575805664, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7693, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011589164131537013, | |
| "eval_loss": 0.6437967419624329, | |
| "eval_runtime": 51.0999, | |
| "eval_samples_per_second": 14.227, | |
| "eval_steps_per_second": 7.123, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014486455164421265, | |
| "grad_norm": 1.3060282468795776, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6705, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017383746197305518, | |
| "grad_norm": 0.9407294988632202, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017383746197305518, | |
| "eval_loss": 0.5756476521492004, | |
| "eval_runtime": 51.0762, | |
| "eval_samples_per_second": 14.234, | |
| "eval_steps_per_second": 7.127, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020281037230189772, | |
| "grad_norm": 0.9185161590576172, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5949, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023178328263074026, | |
| "grad_norm": 1.5283730030059814, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5368, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023178328263074026, | |
| "eval_loss": 0.5568723678588867, | |
| "eval_runtime": 51.2343, | |
| "eval_samples_per_second": 14.19, | |
| "eval_steps_per_second": 7.105, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02607561929595828, | |
| "grad_norm": 1.2832210063934326, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5606, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02897291032884253, | |
| "grad_norm": 1.138390302658081, | |
| "learning_rate": 0.0, | |
| "loss": 0.566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02897291032884253, | |
| "eval_loss": 0.5524906516075134, | |
| "eval_runtime": 51.2238, | |
| "eval_samples_per_second": 14.193, | |
| "eval_steps_per_second": 7.106, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |