| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014713996689350745, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002942799337870149, | |
| "grad_norm": 3.3562655448913574, | |
| "learning_rate": 1e-05, | |
| "loss": 4.2731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002942799337870149, | |
| "eval_loss": 5.133761882781982, | |
| "eval_runtime": 129.5199, | |
| "eval_samples_per_second": 4.424, | |
| "eval_steps_per_second": 2.216, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005885598675740298, | |
| "grad_norm": 3.37448787689209, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4918, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005885598675740298, | |
| "eval_loss": 5.0230865478515625, | |
| "eval_runtime": 33.3326, | |
| "eval_samples_per_second": 17.19, | |
| "eval_steps_per_second": 8.61, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008828398013610447, | |
| "grad_norm": 3.437635660171509, | |
| "learning_rate": 3e-05, | |
| "loss": 4.4412, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011771197351480595, | |
| "grad_norm": 3.1149227619171143, | |
| "learning_rate": 4e-05, | |
| "loss": 4.0714, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011771197351480595, | |
| "eval_loss": 4.873575210571289, | |
| "eval_runtime": 33.3659, | |
| "eval_samples_per_second": 17.173, | |
| "eval_steps_per_second": 8.602, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014713996689350745, | |
| "grad_norm": 2.740934133529663, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7745, | |
| "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": 648596517027840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |