| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.976, | |
| "eval_steps": 500, | |
| "global_step": 186, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0276, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8115, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7782, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5044, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5173, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 1.941, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1896, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4559, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7852, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6719, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4681, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.581, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3833, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4453, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8454, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.605, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7273, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4928, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3592, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4555, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7814, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9702, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7386, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5286, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4299, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3375, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3909, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6683, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8606, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4344, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9833, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6625, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6241, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2086, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2527, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.231, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6654, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6974, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7472, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7494, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3061, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2908, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2471, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4795, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6725, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7614, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.452, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.52, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4723, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3179, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2664, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9138, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6798, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6716, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5811, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4369, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0898, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1264, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3378, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4177, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5868, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7034, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5494, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4917, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4009, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1435, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2246, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2992, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1456, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6365, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5837, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3038, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1338, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1426, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3578, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2643, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4978, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7535, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5326, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4421, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0652, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1587, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4067, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3189, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8257, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3862, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3753, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1937, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1223, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9919, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3945, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2668, | |
| "step": 186 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 6323175937130496.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |