| { | |
| "best_metric": 0.337873637676239, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-120", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 1.0986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.0986, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.0986, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.0972, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.0977, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.0939, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0958, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 1.0946, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0938, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.0854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.0961, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 1.0919, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0767, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.9537037037037035e-05, | |
| "loss": 1.0857, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 1.0621, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.0427, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.0241, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.768518518518519e-05, | |
| "loss": 1.0591, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.0047, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.675925925925926e-05, | |
| "loss": 1.0098, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.031, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.9948, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 1.0092, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.490740740740741e-05, | |
| "loss": 0.9855, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9307, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.9349, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.9556, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.9409, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.8685, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.212962962962963e-05, | |
| "loss": 0.9872, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.9291, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.1203703703703705e-05, | |
| "loss": 0.8922, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.7598, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.8088, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.9518, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.881, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.7904, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.8425925925925924e-05, | |
| "loss": 0.8202, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.864, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.7826, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8987341772151899, | |
| "eval_f1_macro": 0.8729019518493204, | |
| "eval_f1_micro": 0.8987341772151899, | |
| "eval_f1_weighted": 0.8941903089138267, | |
| "eval_loss": 0.6847649812698364, | |
| "eval_precision_macro": 0.9088319088319089, | |
| "eval_precision_micro": 0.8987341772151899, | |
| "eval_precision_weighted": 0.9140971546034837, | |
| "eval_recall_macro": 0.8681818181818182, | |
| "eval_recall_micro": 0.8987341772151899, | |
| "eval_recall_weighted": 0.8987341772151899, | |
| "eval_runtime": 2.8429, | |
| "eval_samples_per_second": 27.789, | |
| "eval_steps_per_second": 1.759, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.8389, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.6574074074074076e-05, | |
| "loss": 0.7693, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.9252, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.564814814814815e-05, | |
| "loss": 0.7749, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 1.0313, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.6687, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.6347, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.3796296296296295e-05, | |
| "loss": 0.7833, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6258, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.2870370370370375e-05, | |
| "loss": 0.7816, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.6796, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.8571, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.6329, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.101851851851852e-05, | |
| "loss": 0.5598, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.9281, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.4988, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.6927, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.8426, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.501, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.824074074074074e-05, | |
| "loss": 0.5604, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.601, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.7314814814814816e-05, | |
| "loss": 0.7268, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 0.6747, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.5498, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.552, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.6723, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6618, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4537037037037038e-05, | |
| "loss": 0.5311, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.4818, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.4142, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.5494, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.2685185185185187e-05, | |
| "loss": 0.4971, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.569, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.175925925925926e-05, | |
| "loss": 0.5328, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 0.5925, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.6497, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.5105, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.990740740740741e-05, | |
| "loss": 0.6727, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.6146, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8981481481481482e-05, | |
| "loss": 0.4375, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9367088607594937, | |
| "eval_f1_macro": 0.9183673469387754, | |
| "eval_f1_micro": 0.9367088607594937, | |
| "eval_f1_weighted": 0.9354172048566262, | |
| "eval_loss": 0.42454662919044495, | |
| "eval_precision_macro": 0.9382716049382717, | |
| "eval_precision_micro": 0.9367088607594937, | |
| "eval_precision_weighted": 0.9484294421003282, | |
| "eval_recall_macro": 0.9166666666666666, | |
| "eval_recall_micro": 0.9367088607594937, | |
| "eval_recall_weighted": 0.9367088607594937, | |
| "eval_runtime": 2.8017, | |
| "eval_samples_per_second": 28.197, | |
| "eval_steps_per_second": 1.785, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3746, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.4894, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.6853, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.712962962962963e-05, | |
| "loss": 0.4073, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.3663, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.3421, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.574074074074074e-05, | |
| "loss": 0.5276, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.4066, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.4587, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.4351851851851853e-05, | |
| "loss": 0.3793, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.4292, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.3425925925925928e-05, | |
| "loss": 0.653, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.286, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.3936, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 0.4646, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.4309, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3694, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0648148148148148e-05, | |
| "loss": 0.4311, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.0185185185185185e-05, | |
| "loss": 0.3337, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.3853, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.328, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.796296296296297e-06, | |
| "loss": 0.4529, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.5029, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.87037037037037e-06, | |
| "loss": 0.3553, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.5009, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.3228, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.3616, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 6.0185185185185185e-06, | |
| "loss": 0.3487, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.2802, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 5.092592592592592e-06, | |
| "loss": 0.2775, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.3091, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.3062, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.266, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.2407407407407406e-06, | |
| "loss": 0.5573, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.3341, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.4007, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.3296, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.4324, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.4967, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.6296296296296297e-07, | |
| "loss": 0.4655, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9367088607594937, | |
| "eval_f1_macro": 0.9183673469387754, | |
| "eval_f1_micro": 0.9367088607594937, | |
| "eval_f1_weighted": 0.9354172048566262, | |
| "eval_loss": 0.337873637676239, | |
| "eval_precision_macro": 0.9382716049382717, | |
| "eval_precision_micro": 0.9367088607594937, | |
| "eval_precision_weighted": 0.9484294421003282, | |
| "eval_recall_macro": 0.9166666666666666, | |
| "eval_recall_micro": 0.9367088607594937, | |
| "eval_recall_weighted": 0.9367088607594937, | |
| "eval_runtime": 2.8079, | |
| "eval_samples_per_second": 28.135, | |
| "eval_steps_per_second": 1.781, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.5886867480312832e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |