| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08859357696567, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017718715393133997, | |
| "grad_norm": 19.056011199951172, | |
| "learning_rate": 1e-05, | |
| "loss": 9.3917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017718715393133997, | |
| "eval_loss": 9.513839721679688, | |
| "eval_runtime": 330.5495, | |
| "eval_samples_per_second": 0.287, | |
| "eval_steps_per_second": 0.145, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.035437430786267994, | |
| "grad_norm": 18.411649703979492, | |
| "learning_rate": 2e-05, | |
| "loss": 9.4516, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.035437430786267994, | |
| "eval_loss": 9.290589332580566, | |
| "eval_runtime": 24.4753, | |
| "eval_samples_per_second": 3.881, | |
| "eval_steps_per_second": 1.961, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 18.850143432617188, | |
| "learning_rate": 3e-05, | |
| "loss": 9.2496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07087486157253599, | |
| "grad_norm": 18.118839263916016, | |
| "learning_rate": 4e-05, | |
| "loss": 8.4158, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07087486157253599, | |
| "eval_loss": 8.082810401916504, | |
| "eval_runtime": 11.9435, | |
| "eval_samples_per_second": 7.954, | |
| "eval_steps_per_second": 4.019, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08859357696567, | |
| "grad_norm": 17.752744674682617, | |
| "learning_rate": 5e-05, | |
| "loss": 7.8917, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4412646277251072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |