| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9206349206349205, | |
| "eval_steps": 500, | |
| "global_step": 232, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018461538461538463, | |
| "loss": 0.9438, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00017964601769911504, | |
| "loss": 0.4303, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00015752212389380532, | |
| "loss": 0.3025, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001353982300884956, | |
| "loss": 0.2458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00011327433628318584, | |
| "loss": 0.2239, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.115044247787611e-05, | |
| "loss": 0.2027, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 6.902654867256638e-05, | |
| "loss": 0.2001, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.690265486725664e-05, | |
| "loss": 0.1922, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.4778761061946905e-05, | |
| "loss": 0.1778, | |
| "step": 225 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 252, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 1.877894115832627e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |