| { | |
| "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": 1.7597, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7691, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7391, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8441, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8435, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 1.946, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8873, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7255, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5998, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3951, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4886, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4517, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4721, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 1.541, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2211, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3493, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 1.369, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3797, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3887, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3289, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2585, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5215, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3621, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1277, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3098, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2836, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3276, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2232, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3009, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3459, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2756, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2275, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 1.266, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3021, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3212, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0714, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2865, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1694, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2996, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002, | |
| "loss": 1.185, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2625, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2019, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2313, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1451, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2957, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1715, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2473, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1796, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 1.211, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1733, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.156, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.124, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2058, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2686, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1246, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1836, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1491, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2865, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1011, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002, | |
| "loss": 1.267, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.128, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1364, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0983, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0923, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.142, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1277, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0157, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9849, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2084, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1842, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2013, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1305, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1419, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1472, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9259, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1574, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2082, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2029, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1883, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1662, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1388, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0185, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9262, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2859, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2683, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0533, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 1.095, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0904, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0844, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9657, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0686, | |
| "step": 186 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 4225580494577664.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |