| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 28.571428571428573, | |
| "eval_steps": 500, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8155, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0001, | |
| "loss": 1.848, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.8329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8311, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.00019444444444444446, | |
| "loss": 1.8991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00018888888888888888, | |
| "loss": 1.7408, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00018333333333333334, | |
| "loss": 1.8108, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 1.8031, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 0.00017222222222222224, | |
| "loss": 1.7605, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.7367, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.0001611111111111111, | |
| "loss": 1.7215, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 1.7342, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.7194, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00014444444444444444, | |
| "loss": 1.6771, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 0.0001388888888888889, | |
| "loss": 1.6938, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.5943, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 0.00012777777777777776, | |
| "loss": 1.686, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 0.00012222222222222224, | |
| "loss": 1.6046, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 0.00011666666666666668, | |
| "loss": 1.5834, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 1.6078, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.00010555555555555557, | |
| "loss": 1.5769, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5473, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 9.444444444444444e-05, | |
| "loss": 1.5717, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 1.5053, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.5388, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 1.4342, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 1.5222, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.4665, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 20.71, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 1.4485, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 1.4478, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 22.14, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4553, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.4205, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.4115, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.3992, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.4159, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.3851, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.3877, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.4048, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 1.3533, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.0, | |
| "loss": 1.3752, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 80, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 6.5185089847296e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |