| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 66.66666666666667, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7473, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4e-05, | |
| "loss": 1.69, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7306, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7116, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7313, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6886, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7171, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00016, | |
| "loss": 1.6503, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00018, | |
| "loss": 1.648, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6006, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 0.00019777777777777778, | |
| "loss": 1.5927, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00019555555555555556, | |
| "loss": 1.5831, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 0.00019333333333333333, | |
| "loss": 1.5099, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.00019111111111111114, | |
| "loss": 1.443, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00018888888888888888, | |
| "loss": 1.465, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 1.4726, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 0.00018444444444444446, | |
| "loss": 1.3746, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.00018222222222222224, | |
| "loss": 1.3903, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 0.00018, | |
| "loss": 1.354, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 1.3862, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 0.00017555555555555556, | |
| "loss": 1.3473, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 0.00017333333333333334, | |
| "loss": 1.3259, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 0.0001711111111111111, | |
| "loss": 1.3708, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 0.00016888888888888889, | |
| "loss": 1.2815, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.2665, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 0.00016444444444444444, | |
| "loss": 1.334, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 0.00016222222222222224, | |
| "loss": 1.2575, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2478, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "learning_rate": 0.0001577777777777778, | |
| "loss": 1.2474, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 1.2455, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 20.67, | |
| "learning_rate": 0.00015333333333333334, | |
| "loss": 1.1969, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 0.0001511111111111111, | |
| "loss": 1.2369, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 0.0001488888888888889, | |
| "loss": 1.2038, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "learning_rate": 0.00014666666666666666, | |
| "loss": 1.179, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 0.00014444444444444444, | |
| "loss": 1.1484, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 0.00014222222222222224, | |
| "loss": 1.196, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 24.67, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1739, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 25.33, | |
| "learning_rate": 0.0001377777777777778, | |
| "loss": 1.1176, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 0.00013555555555555556, | |
| "loss": 1.1151, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.0642, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 0.00013111111111111111, | |
| "loss": 1.1203, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 0.00012888888888888892, | |
| "loss": 1.0962, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 28.67, | |
| "learning_rate": 0.00012666666666666666, | |
| "loss": 1.0606, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 29.33, | |
| "learning_rate": 0.00012444444444444444, | |
| "loss": 1.0825, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.00012222222222222224, | |
| "loss": 1.0042, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0551, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 31.33, | |
| "learning_rate": 0.00011777777777777779, | |
| "loss": 0.9581, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 0.00011555555555555555, | |
| "loss": 0.9902, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 32.67, | |
| "learning_rate": 0.00011333333333333334, | |
| "loss": 0.9915, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.9637, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 0.00010888888888888889, | |
| "loss": 0.8967, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 34.67, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 0.9312, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 35.33, | |
| "learning_rate": 0.00010444444444444445, | |
| "loss": 0.8629, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 0.00010222222222222222, | |
| "loss": 0.9007, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 36.67, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8208, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 37.33, | |
| "learning_rate": 9.777777777777778e-05, | |
| "loss": 0.8691, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 9.555555555555557e-05, | |
| "loss": 0.8424, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 38.67, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.7912, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 39.33, | |
| "learning_rate": 9.111111111111112e-05, | |
| "loss": 0.8062, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.7743, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 40.67, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 0.7413, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 41.33, | |
| "learning_rate": 8.444444444444444e-05, | |
| "loss": 0.7732, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 8.222222222222222e-05, | |
| "loss": 0.691, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 42.67, | |
| "learning_rate": 8e-05, | |
| "loss": 0.719, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 43.33, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.68, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 7.555555555555556e-05, | |
| "loss": 0.6434, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 44.67, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 0.6415, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 45.33, | |
| "learning_rate": 7.111111111111112e-05, | |
| "loss": 0.6421, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 6.88888888888889e-05, | |
| "loss": 0.593, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 46.67, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.6038, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 47.33, | |
| "learning_rate": 6.444444444444446e-05, | |
| "loss": 0.5586, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 6.222222222222222e-05, | |
| "loss": 0.5388, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 48.67, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5099, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 49.33, | |
| "learning_rate": 5.7777777777777776e-05, | |
| "loss": 0.515, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.4512, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 50.67, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.4653, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 51.33, | |
| "learning_rate": 5.111111111111111e-05, | |
| "loss": 0.4577, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.4005, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 52.67, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.4214, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.3747, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.4205, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 54.67, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3831, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 55.33, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.3918, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.3339, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 56.67, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3476, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 57.33, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.3224, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.3523, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 58.67, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.351, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 59.33, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.3076, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.2934, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 60.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.318, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 61.33, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.3103, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.2663, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 62.67, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.2584, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 63.33, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3059, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.2872, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 64.67, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2621, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 65.33, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.2649, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.2978, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 0.0, | |
| "loss": 0.2732, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 6.50352940548096e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |