| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1, | |
| "eval_steps": 10, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.4549098196392788e-05, | |
| "loss": 1.5765, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.4641923904418945, | |
| "eval_runtime": 221.9956, | |
| "eval_samples_per_second": 0.901, | |
| "eval_steps_per_second": 0.113, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.404809619238477e-05, | |
| "loss": 1.5681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.4410793781280518, | |
| "eval_runtime": 221.7333, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.3547094188376757e-05, | |
| "loss": 1.2801, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.4293081760406494, | |
| "eval_runtime": 221.7604, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.304609218436874e-05, | |
| "loss": 1.5474, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.430722951889038, | |
| "eval_runtime": 221.7555, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "total_flos": 6907873198080000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |