| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 848, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.95e-05, | |
| "loss": 6.3714, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.850927352905273, | |
| "eval_runtime": 3.8282, | |
| "eval_samples_per_second": 176.584, | |
| "eval_steps_per_second": 22.204, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 5.5438, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 4.862037658691406, | |
| "eval_runtime": 3.7425, | |
| "eval_samples_per_second": 180.626, | |
| "eval_steps_per_second": 22.712, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.850000000000001e-05, | |
| "loss": 4.6993, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 4.018372058868408, | |
| "eval_runtime": 4.0424, | |
| "eval_samples_per_second": 167.229, | |
| "eval_steps_per_second": 21.027, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.8e-05, | |
| "loss": 3.967, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.290557384490967, | |
| "eval_runtime": 4.3933, | |
| "eval_samples_per_second": 153.872, | |
| "eval_steps_per_second": 19.348, | |
| "step": 848 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 42400, | |
| "num_train_epochs": 200, | |
| "save_steps": 500, | |
| "total_flos": 1137839826710832.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |