| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07944389275074479, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015888778550148957, | |
| "grad_norm": 0.439314067363739, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6587, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015888778550148957, | |
| "eval_loss": 0.9841099977493286, | |
| "eval_runtime": 78.6055, | |
| "eval_samples_per_second": 1.349, | |
| "eval_steps_per_second": 0.674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.031777557100297914, | |
| "grad_norm": 0.5920372009277344, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8999, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.031777557100297914, | |
| "eval_loss": 0.969989538192749, | |
| "eval_runtime": 3.8382, | |
| "eval_samples_per_second": 27.617, | |
| "eval_steps_per_second": 13.808, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.047666335650446874, | |
| "grad_norm": 0.44349122047424316, | |
| "learning_rate": 3e-05, | |
| "loss": 0.726, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06355511420059583, | |
| "grad_norm": 0.5145066976547241, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7629, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06355511420059583, | |
| "eval_loss": 0.9453964233398438, | |
| "eval_runtime": 3.84, | |
| "eval_samples_per_second": 27.604, | |
| "eval_steps_per_second": 13.802, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07944389275074479, | |
| "grad_norm": 0.5710826516151428, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5971, | |
| "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": 5733649169252352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |