| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.902439024390244, | |
| "eval_steps": 5, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.07996653020381927, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "eval_runtime": 48.4614, | |
| "eval_samples_per_second": 5.798, | |
| "eval_steps_per_second": 0.371, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 0.10972072184085846, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7133, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "eval_runtime": 48.1459, | |
| "eval_samples_per_second": 5.836, | |
| "eval_steps_per_second": 0.374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 0.13606426119804382, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "eval_runtime": 47.77, | |
| "eval_samples_per_second": 5.882, | |
| "eval_steps_per_second": 0.377, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.902439024390244, | |
| "grad_norm": 0.14128075540065765, | |
| "learning_rate": 5e-05, | |
| "loss": 1.518, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0407585245036544e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |