| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5642544787699252, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.0211480362537768e-05, | |
| "loss": 1.4914, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3.985424375207197e-05, | |
| "loss": 1.103, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.910964926929347e-05, | |
| "loss": 1.1117, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.775641735336502e-05, | |
| "loss": 1.1636, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.583764809409783e-05, | |
| "loss": 1.1947, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.34144538007923e-05, | |
| "loss": 1.1979, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.05640125908444e-05, | |
| "loss": 1.4767, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.1554332626816203e-05, | |
| "loss": 0.9765, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.9009680903546416e-05, | |
| "loss": 1.4107, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.6260730367115988e-05, | |
| "loss": 1.5024, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.9542651711125413e-05, | |
| "loss": 0.975, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.7394824453041223e-05, | |
| "loss": 1.1808, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.5133790365330005e-05, | |
| "loss": 1.1449, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.2799977645691646e-05, | |
| "loss": 1.4763, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.0426471341395805e-05, | |
| "loss": 1.6014, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.8046919211584273e-05, | |
| "loss": 1.6065, | |
| "step": 8000 | |
| } | |
| ], | |
| "max_steps": 14178, | |
| "num_train_epochs": 1, | |
| "total_flos": 8919658633003008.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |