| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9334889148191365, | |
| "eval_steps": 250, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.46674445740956827, | |
| "grad_norm": 6.355308532714844, | |
| "learning_rate": 9.899294610497411e-05, | |
| "loss": 3.4363, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.46674445740956827, | |
| "eval_loss": 0.2021917849779129, | |
| "eval_runtime": 11.2146, | |
| "eval_samples_per_second": 7.758, | |
| "eval_steps_per_second": 7.758, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9334889148191365, | |
| "grad_norm": 2.1196815967559814, | |
| "learning_rate": 9.378729871108362e-05, | |
| "loss": 1.1086, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9334889148191365, | |
| "eval_loss": 0.13436643779277802, | |
| "eval_runtime": 11.2216, | |
| "eval_samples_per_second": 7.753, | |
| "eval_steps_per_second": 7.753, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 2675, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.874250259759104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |