| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3799969600243198, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.90500075999392e-05, | |
| "loss": 7.8228, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.81000151998784e-05, | |
| "loss": 7.1961, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.7150022799817604e-05, | |
| "loss": 7.0021, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.620003039975681e-05, | |
| "loss": 6.9097, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5250037999696e-05, | |
| "loss": 6.8192, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4300045599635205e-05, | |
| "loss": 6.7572, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.33500531995744e-05, | |
| "loss": 6.6217, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.240006079951361e-05, | |
| "loss": 6.5452, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.145006839945281e-05, | |
| "loss": 6.5289, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.050007599939201e-05, | |
| "loss": 6.438, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9550083599331206e-05, | |
| "loss": 6.4793, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.860009119927041e-05, | |
| "loss": 6.3968, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.765009879920961e-05, | |
| "loss": 6.3745, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.670010639914881e-05, | |
| "loss": 6.2876, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.575011399908801e-05, | |
| "loss": 6.2033, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.4800121599027206e-05, | |
| "loss": 6.157, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.3850129198966415e-05, | |
| "loss": 6.1427, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.290013679890561e-05, | |
| "loss": 6.0376, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.1950144398844814e-05, | |
| "loss": 5.9889, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.100015199878401e-05, | |
| "loss": 5.9469, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 26316, | |
| "num_train_epochs": 1, | |
| "total_flos": 1081315260879360.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |