| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.014166666666668, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 11.0133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00025, | |
| "loss": 8.26, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0005, | |
| "loss": 6.2745, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.0005833333333333333, | |
| "loss": 5.6705, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 0.0005555555555555556, | |
| "loss": 5.3288, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 0.0005277777777777777, | |
| "loss": 5.1396, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 0.0005, | |
| "loss": 4.9995, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 0.00047222222222222224, | |
| "loss": 4.7272, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 0.00044444444444444436, | |
| "loss": 4.6129, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 0.00041666666666666664, | |
| "loss": 4.4105, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 0.00038888888888888887, | |
| "loss": 4.2453, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 0.0003611111111111111, | |
| "loss": 4.1117, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 0.0003333333333333333, | |
| "loss": 3.9934, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 0.00030555555555555555, | |
| "loss": 3.8898, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 0.0002777777777777778, | |
| "loss": 3.7236, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 0.00025, | |
| "loss": 3.7193, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 0.00022222222222222218, | |
| "loss": 3.646, | |
| "step": 800 | |
| } | |
| ], | |
| "max_steps": 1200, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.21582436728832e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |