| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 11.155705996131529, | |
| "eval_steps": 500, | |
| "global_step": 5796, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.3306473274241204e-05, | |
| "loss": 1.0675, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.661294654848241e-05, | |
| "loss": 0.9002, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.991941982272361e-05, | |
| "loss": 0.8503, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.00013322589309696482, | |
| "loss": 0.8105, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.00016653236637120602, | |
| "loss": 0.777, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.00019983883964544723, | |
| "loss": 0.7484, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 0.00019631652786483987, | |
| "loss": 0.7206, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 0.0001926151458165428, | |
| "loss": 0.6861, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 0.00018891376376824575, | |
| "loss": 0.6591, | |
| "step": 5580 | |
| } | |
| ], | |
| "logging_steps": 620, | |
| "max_steps": 37224, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "total_flos": 4.0542745809597235e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |