| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7143, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6969, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6016, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4545, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3691, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2808, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2052, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0442, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9511, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8863, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7961, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.72, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6786, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6351, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5312, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5145, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6165, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5138, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5425, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5166, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4996, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5757, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5183, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5349, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4842, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4626, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4677, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4644, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4195, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.498, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4685, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4256, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4406, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3847, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4039, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3879, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3924, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4439, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4041, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3852, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3492, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3613, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.381, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3581, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3238, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3031, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.265, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3163, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3281, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6814, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6904, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6387, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6075, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5507, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5008, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5305, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4997, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4824, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5156, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4761, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5306, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4929, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4895, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5044, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5326, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5032, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4838, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4525, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4486, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4566, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4455, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4226, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4411, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4551, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 250, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "total_flos": 6048210105630720.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |