| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 59008, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.998305371970854e-06, | |
| "loss": 0.2287, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.889223642834279e-06, | |
| "loss": 0.0003, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.778258986574275e-06, | |
| "loss": 0.0001, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.667294330314271e-06, | |
| "loss": 0.0002, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.556329674054268e-06, | |
| "loss": 0.0001, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.445365017794265e-06, | |
| "loss": 0.0, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.334400361534261e-06, | |
| "loss": 0.0, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.223435705274258e-06, | |
| "loss": 0.0, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.1124710490142543e-06, | |
| "loss": 0.0, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.5063927542508523e-09, | |
| "loss": 0.0, | |
| "step": 59000 | |
| } | |
| ], | |
| "logging_steps": 5900, | |
| "max_steps": 59008, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 1.1409827659776e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |