| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.188361408882082, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.8468606431852985e-06, | |
| "loss": 0.4586, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.6937212863705971e-06, | |
| "loss": 0.1973, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.5405819295558958e-06, | |
| "loss": 0.1644, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.3874425727411944e-06, | |
| "loss": 0.1565, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.234303215926493e-06, | |
| "loss": 0.1154, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.0811638591117918e-06, | |
| "loss": 0.0989, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 9.280245022970902e-07, | |
| "loss": 0.0942, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 7.74885145482389e-07, | |
| "loss": 0.0812, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 6.217457886676876e-07, | |
| "loss": 0.0692, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 4.686064318529862e-07, | |
| "loss": 0.0796, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 3.1546707503828487e-07, | |
| "loss": 0.0582, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 1.6232771822358346e-07, | |
| "loss": 0.0495, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6530, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 5587394488833024.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |