| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.818181818181818, | |
| "eval_steps": 500, | |
| "global_step": 135, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.1098, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.1831, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 1.1273, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 1.1295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00011764705882352942, | |
| "loss": 1.0906, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0001411764705882353, | |
| "loss": 1.0239, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0001647058823529412, | |
| "loss": 0.9996, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00018823529411764707, | |
| "loss": 0.8502, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00019864864864864865, | |
| "loss": 0.8154, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00019594594594594594, | |
| "loss": 0.71, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00019324324324324326, | |
| "loss": 0.7255, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.00019054054054054055, | |
| "loss": 0.6063, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00018783783783783784, | |
| "loss": 0.6039, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00018513513513513513, | |
| "loss": 0.5068, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00018243243243243245, | |
| "loss": 0.5053, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.00017972972972972974, | |
| "loss": 0.4882, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.00017702702702702703, | |
| "loss": 0.4442, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.00017432432432432432, | |
| "loss": 0.5363, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 0.00017162162162162164, | |
| "loss": 0.4253, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00016891891891891893, | |
| "loss": 0.408, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 0.00016621621621621622, | |
| "loss": 0.3472, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0001635135135135135, | |
| "loss": 0.354, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00016081081081081083, | |
| "loss": 0.3762, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00015810810810810812, | |
| "loss": 0.3216, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.0001554054054054054, | |
| "loss": 0.2651, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 0.0001527027027027027, | |
| "loss": 0.2992, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.282, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.0001472972972972973, | |
| "loss": 0.239, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 0.00014459459459459462, | |
| "loss": 0.2548, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.00014189189189189188, | |
| "loss": 0.2259, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 0.0001391891891891892, | |
| "loss": 0.2364, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 0.0001364864864864865, | |
| "loss": 0.1785, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 0.0001337837837837838, | |
| "loss": 0.1864, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 0.00013108108108108107, | |
| "loss": 0.1786, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 0.0001283783783783784, | |
| "loss": 0.1585, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 0.00012567567567567568, | |
| "loss": 0.1964, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 0.000122972972972973, | |
| "loss": 0.1177, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 0.00012027027027027027, | |
| "loss": 0.1259, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.00011756756756756758, | |
| "loss": 0.1448, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 0.00011486486486486487, | |
| "loss": 0.1562, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.00011216216216216217, | |
| "loss": 0.1193, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 0.00010945945945945946, | |
| "loss": 0.1375, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 0.00010675675675675677, | |
| "loss": 0.1109, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 0.00010405405405405406, | |
| "loss": 0.0994, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 0.00010135135135135136, | |
| "loss": 0.0918, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 9.864864864864865e-05, | |
| "loss": 0.0779, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 9.594594594594595e-05, | |
| "loss": 0.0748, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 9.324324324324324e-05, | |
| "loss": 0.087, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 9.054054054054055e-05, | |
| "loss": 0.0914, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 8.783783783783784e-05, | |
| "loss": 0.0768, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 8.513513513513514e-05, | |
| "loss": 0.0619, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 8.243243243243243e-05, | |
| "loss": 0.0764, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 7.972972972972974e-05, | |
| "loss": 0.0531, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 7.702702702702703e-05, | |
| "loss": 0.0571, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 7.432432432432433e-05, | |
| "loss": 0.0513, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 7.162162162162162e-05, | |
| "loss": 0.0478, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 6.891891891891892e-05, | |
| "loss": 0.0532, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 6.621621621621621e-05, | |
| "loss": 0.0535, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 6.351351351351352e-05, | |
| "loss": 0.0415, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 6.0810810810810814e-05, | |
| "loss": 0.0449, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 5.8108108108108105e-05, | |
| "loss": 0.0507, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 5.540540540540541e-05, | |
| "loss": 0.0411, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 5.27027027027027e-05, | |
| "loss": 0.0397, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0386, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 4.72972972972973e-05, | |
| "loss": 0.0399, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 4.4594594594594596e-05, | |
| "loss": 0.0332, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 4.189189189189189e-05, | |
| "loss": 0.0376, | |
| "step": 134 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 165, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "total_flos": 1.250373390336e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |