| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.26490066225165565, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8.984384775496429e-05, | |
| "loss": 0.6651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.937647473201847e-05, | |
| "loss": 0.5741, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.860112454657597e-05, | |
| "loss": 0.6273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.752317820628772e-05, | |
| "loss": 0.6055, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.615011676631211e-05, | |
| "loss": 0.631, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.449146941004577e-05, | |
| "loss": 0.5563, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.255874731563996e-05, | |
| "loss": 0.5987, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.036536376727568e-05, | |
| "loss": 0.708, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.792654106563294e-05, | |
| "loss": 0.6866, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.525920488360535e-05, | |
| "loss": 0.7099, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.6931471824645996, | |
| "eval_runtime": 18.0135, | |
| "eval_samples_per_second": 139.729, | |
| "eval_steps_per_second": 23.316, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 377, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |