| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0254, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0254, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0181, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0005, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9736, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00019555555555555556, | |
| "loss": 0.9337, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.00019111111111111114, | |
| "loss": 0.8813, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 0.8238, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.00018222222222222224, | |
| "loss": 0.7652, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.7033, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 0.00017333333333333334, | |
| "loss": 0.6398, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.00016888888888888889, | |
| "loss": 0.5863, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 0.00016444444444444444, | |
| "loss": 0.5291, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4743, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 0.4194, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 0.0001511111111111111, | |
| "loss": 0.3678, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 0.00014666666666666666, | |
| "loss": 0.3218, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 0.00014222222222222224, | |
| "loss": 0.279, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 0.0001377777777777778, | |
| "loss": 0.2395, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.2013, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 0.00012888888888888892, | |
| "loss": 0.1709, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 0.00012444444444444444, | |
| "loss": 0.146, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1277, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 0.00011555555555555555, | |
| "loss": 0.112, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.099, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 0.0877, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 0.00010222222222222222, | |
| "loss": 0.079, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 9.777777777777778e-05, | |
| "loss": 0.0709, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.0642, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.0587, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 8.444444444444444e-05, | |
| "loss": 0.0545, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0514, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 7.555555555555556e-05, | |
| "loss": 0.0481, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 7.111111111111112e-05, | |
| "loss": 0.0458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0426, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 6.222222222222222e-05, | |
| "loss": 0.04, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 5.7777777777777776e-05, | |
| "loss": 0.0383, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.0356, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.0333, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0319, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0294, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.0284, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.0284, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0259, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0253, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0242, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0242, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0235, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0232, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0238, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 2075279543500800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |