| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00250244630167311, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.416528978649e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 625.5194, | |
| "eval_samples_per_second": 10.492, | |
| "eval_steps_per_second": 5.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032082644893245, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006416528978649, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006416528978649, | |
| "eval_loss": NaN, | |
| "eval_runtime": 691.5212, | |
| "eval_samples_per_second": 9.491, | |
| "eval_steps_per_second": 4.746, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00096247934679735, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012833057957298, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012833057957298, | |
| "eval_loss": NaN, | |
| "eval_runtime": 693.0537, | |
| "eval_samples_per_second": 9.47, | |
| "eval_steps_per_second": 4.736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00160413224466225, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0019249586935947, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019249586935947, | |
| "eval_loss": NaN, | |
| "eval_runtime": 692.7893, | |
| "eval_samples_per_second": 9.473, | |
| "eval_steps_per_second": 4.737, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00224578514252715, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 420705323974656.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |