| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9975062344139651, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0199501246882793, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.3172, | |
| "eval_samples_per_second": 18.453, | |
| "eval_steps_per_second": 2.348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.3044, | |
| "eval_samples_per_second": 19.533, | |
| "eval_steps_per_second": 2.485, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39900249376558605, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.39900249376558605, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.289, | |
| "eval_samples_per_second": 19.55, | |
| "eval_steps_per_second": 2.487, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5985037406483791, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5985037406483791, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.3528, | |
| "eval_samples_per_second": 19.478, | |
| "eval_steps_per_second": 2.478, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7980049875311721, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7980049875311721, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.3612, | |
| "eval_samples_per_second": 19.469, | |
| "eval_steps_per_second": 2.477, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9975062344139651, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9975062344139651, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.3265, | |
| "eval_samples_per_second": 19.508, | |
| "eval_steps_per_second": 2.482, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 1.394108836872192e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |