| { | |
| "best_metric": 0.8072579503059387, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-190", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 190, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.263157894736843e-06, | |
| "loss": 1.6094, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.0526315789473686e-05, | |
| "loss": 1.6094, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 1.6096, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.1052631578947372e-05, | |
| "loss": 1.6089, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.6085, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 1.6068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.68421052631579e-05, | |
| "loss": 1.6105, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.2105263157894745e-05, | |
| "loss": 1.6058, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 1.6108, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.2631578947368424e-05, | |
| "loss": 1.6079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.7894736842105274e-05, | |
| "loss": 1.6044, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.31578947368421e-05, | |
| "loss": 1.6069, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.842105263157895e-05, | |
| "loss": 1.6007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.36842105263158e-05, | |
| "loss": 1.6083, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 7.894736842105263e-05, | |
| "loss": 1.6077, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.421052631578949e-05, | |
| "loss": 1.5968, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.947368421052632e-05, | |
| "loss": 1.5903, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.473684210526316e-05, | |
| "loss": 1.6045, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5974, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3076923076923077, | |
| "eval_f1_macro": 0.09411764705882353, | |
| "eval_f1_micro": 0.3076923076923077, | |
| "eval_f1_weighted": 0.14479638009049772, | |
| "eval_loss": 1.5974059104919434, | |
| "eval_precision_macro": 0.06153846153846154, | |
| "eval_precision_micro": 0.3076923076923077, | |
| "eval_precision_weighted": 0.09467455621301776, | |
| "eval_recall_macro": 0.2, | |
| "eval_recall_micro": 0.3076923076923077, | |
| "eval_recall_weighted": 0.3076923076923077, | |
| "eval_runtime": 0.2784, | |
| "eval_samples_per_second": 140.073, | |
| "eval_steps_per_second": 10.775, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00010526315789473685, | |
| "loss": 1.5782, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00011052631578947368, | |
| "loss": 1.5568, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00011578947368421055, | |
| "loss": 1.603, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00011578947368421055, | |
| "loss": 1.5393, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00012105263157894738, | |
| "loss": 1.5972, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001263157894736842, | |
| "loss": 1.6077, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00013157894736842105, | |
| "loss": 1.5841, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0001368421052631579, | |
| "loss": 1.5846, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00014210526315789476, | |
| "loss": 1.5916, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001473684210526316, | |
| "loss": 1.5476, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00015263157894736842, | |
| "loss": 1.6294, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 1.571, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0001631578947368421, | |
| "loss": 1.6475, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00016842105263157898, | |
| "loss": 1.5652, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001736842105263158, | |
| "loss": 1.5198, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00017894736842105264, | |
| "loss": 1.5658, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00018421052631578948, | |
| "loss": 1.5823, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00018947368421052632, | |
| "loss": 1.5813, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00019473684210526317, | |
| "loss": 1.5338, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3076923076923077, | |
| "eval_f1_macro": 0.09411764705882353, | |
| "eval_f1_micro": 0.3076923076923077, | |
| "eval_f1_weighted": 0.14479638009049772, | |
| "eval_loss": 1.571889877319336, | |
| "eval_precision_macro": 0.06153846153846154, | |
| "eval_precision_micro": 0.3076923076923077, | |
| "eval_precision_weighted": 0.09467455621301776, | |
| "eval_recall_macro": 0.2, | |
| "eval_recall_micro": 0.3076923076923077, | |
| "eval_recall_weighted": 0.3076923076923077, | |
| "eval_runtime": 0.1048, | |
| "eval_samples_per_second": 372.122, | |
| "eval_steps_per_second": 28.625, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5117, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00020526315789473685, | |
| "loss": 1.4995, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0002105263157894737, | |
| "loss": 1.6392, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.00021578947368421054, | |
| "loss": 1.4529, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00022105263157894735, | |
| "loss": 1.5848, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002263157894736842, | |
| "loss": 1.5591, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002315789473684211, | |
| "loss": 1.5641, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002368421052631579, | |
| "loss": 1.499, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00024210526315789475, | |
| "loss": 1.6476, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002473684210526316, | |
| "loss": 1.4727, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002526315789473684, | |
| "loss": 1.5519, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0002578947368421053, | |
| "loss": 1.5057, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0002631578947368421, | |
| "loss": 1.6801, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00026842105263157897, | |
| "loss": 1.5518, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002736842105263158, | |
| "loss": 1.4608, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002789473684210526, | |
| "loss": 1.5961, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002842105263157895, | |
| "loss": 1.3564, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.00028947368421052634, | |
| "loss": 1.5493, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0002947368421052632, | |
| "loss": 1.5723, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3076923076923077, | |
| "eval_f1_macro": 0.09411764705882353, | |
| "eval_f1_micro": 0.3076923076923077, | |
| "eval_f1_weighted": 0.14479638009049772, | |
| "eval_loss": 1.5472002029418945, | |
| "eval_precision_macro": 0.06153846153846154, | |
| "eval_precision_micro": 0.3076923076923077, | |
| "eval_precision_weighted": 0.09467455621301776, | |
| "eval_recall_macro": 0.2, | |
| "eval_recall_micro": 0.3076923076923077, | |
| "eval_recall_weighted": 0.3076923076923077, | |
| "eval_runtime": 0.1034, | |
| "eval_samples_per_second": 377.243, | |
| "eval_steps_per_second": 29.019, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00030000000000000003, | |
| "loss": 1.3807, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.00030526315789473684, | |
| "loss": 1.4009, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.0003105263157894737, | |
| "loss": 1.3475, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00031578947368421053, | |
| "loss": 1.4923, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.0003210526315789474, | |
| "loss": 1.3802, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 0.0003263157894736842, | |
| "loss": 1.4757, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 0.00033157894736842103, | |
| "loss": 1.4177, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.00033684210526315796, | |
| "loss": 1.7288, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.00034210526315789477, | |
| "loss": 1.4219, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.0003473684210526316, | |
| "loss": 1.6314, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.00035263157894736846, | |
| "loss": 1.5195, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.0003578947368421053, | |
| "loss": 1.4379, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.00036315789473684214, | |
| "loss": 1.6594, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.00036842105263157896, | |
| "loss": 1.5372, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 0.0003736842105263158, | |
| "loss": 1.6277, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.00037894736842105265, | |
| "loss": 1.3156, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.00038421052631578946, | |
| "loss": 1.7242, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00038947368421052633, | |
| "loss": 1.4844, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0003947368421052632, | |
| "loss": 1.4152, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3076923076923077, | |
| "eval_f1_macro": 0.09411764705882353, | |
| "eval_f1_micro": 0.3076923076923077, | |
| "eval_f1_weighted": 0.14479638009049772, | |
| "eval_loss": 1.4960436820983887, | |
| "eval_precision_macro": 0.06153846153846154, | |
| "eval_precision_micro": 0.3076923076923077, | |
| "eval_precision_weighted": 0.09467455621301776, | |
| "eval_recall_macro": 0.2, | |
| "eval_recall_micro": 0.3076923076923077, | |
| "eval_recall_weighted": 0.3076923076923077, | |
| "eval_runtime": 0.1073, | |
| "eval_samples_per_second": 363.387, | |
| "eval_steps_per_second": 27.953, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0004, | |
| "loss": 1.2319, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.0004052631578947369, | |
| "loss": 1.5189, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.0004105263157894737, | |
| "loss": 1.5146, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.0004157894736842105, | |
| "loss": 1.4695, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.0004210526315789474, | |
| "loss": 1.343, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 0.0004263157894736842, | |
| "loss": 1.4702, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.0004315789473684211, | |
| "loss": 1.6262, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 0.0004368421052631579, | |
| "loss": 1.5298, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.0004421052631578947, | |
| "loss": 1.2922, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 0.0004473684210526316, | |
| "loss": 1.2764, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.0004526315789473684, | |
| "loss": 1.2834, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.00045789473684210527, | |
| "loss": 1.3713, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0004631578947368422, | |
| "loss": 1.5645, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 0.000468421052631579, | |
| "loss": 1.3019, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.0004736842105263158, | |
| "loss": 1.3534, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.0004789473684210527, | |
| "loss": 1.4572, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0004842105263157895, | |
| "loss": 1.5372, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0004894736842105264, | |
| "loss": 1.4614, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0004947368421052632, | |
| "loss": 1.214, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.41025641025641024, | |
| "eval_f1_macro": 0.21165501165501163, | |
| "eval_f1_micro": 0.41025641025641024, | |
| "eval_f1_weighted": 0.29765106688183607, | |
| "eval_loss": 1.392277717590332, | |
| "eval_precision_macro": 0.17407407407407408, | |
| "eval_precision_micro": 0.41025641025641024, | |
| "eval_precision_weighted": 0.24216524216524218, | |
| "eval_recall_macro": 0.2866666666666667, | |
| "eval_recall_micro": 0.41025641025641024, | |
| "eval_recall_weighted": 0.41025641025641024, | |
| "eval_runtime": 0.1067, | |
| "eval_samples_per_second": 365.557, | |
| "eval_steps_per_second": 28.12, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0005, | |
| "loss": 1.1431, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0005052631578947368, | |
| "loss": 1.1986, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0005105263157894738, | |
| "loss": 1.3605, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 0.0005157894736842106, | |
| "loss": 1.4709, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.0005210526315789474, | |
| "loss": 1.4103, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0005263157894736842, | |
| "loss": 1.5161, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.000531578947368421, | |
| "loss": 1.4339, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 0.0005368421052631579, | |
| "loss": 1.2471, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 0.0005421052631578948, | |
| "loss": 1.3335, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.0005473684210526316, | |
| "loss": 1.1644, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 0.0005526315789473684, | |
| "loss": 1.5695, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 0.0005578947368421052, | |
| "loss": 1.099, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 0.0005631578947368421, | |
| "loss": 1.3556, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 0.000568421052631579, | |
| "loss": 1.4156, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 0.0005736842105263159, | |
| "loss": 1.3777, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.0005789473684210527, | |
| "loss": 1.8594, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.0005842105263157895, | |
| "loss": 0.995, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.0005894736842105264, | |
| "loss": 1.2018, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0005947368421052632, | |
| "loss": 0.9971, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.48717948717948717, | |
| "eval_f1_macro": 0.33415204678362576, | |
| "eval_f1_micro": 0.48717948717948717, | |
| "eval_f1_weighted": 0.4098065677013045, | |
| "eval_loss": 1.2535957098007202, | |
| "eval_precision_macro": 0.35025641025641024, | |
| "eval_precision_micro": 0.48717948717948717, | |
| "eval_precision_weighted": 0.4003944773175543, | |
| "eval_recall_macro": 0.3733333333333333, | |
| "eval_recall_micro": 0.48717948717948717, | |
| "eval_recall_weighted": 0.48717948717948717, | |
| "eval_runtime": 0.1096, | |
| "eval_samples_per_second": 355.926, | |
| "eval_steps_per_second": 27.379, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.0006000000000000001, | |
| "loss": 1.1295, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.0006052631578947369, | |
| "loss": 1.4946, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 0.0006105263157894737, | |
| "loss": 1.8178, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.0006157894736842106, | |
| "loss": 1.1574, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.0006210526315789474, | |
| "loss": 0.9329, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 0.0006263157894736842, | |
| "loss": 1.2374, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 0.0006315789473684211, | |
| "loss": 1.5585, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 0.0006368421052631579, | |
| "loss": 1.0872, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 0.0006421052631578948, | |
| "loss": 0.9432, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.0006473684210526316, | |
| "loss": 1.2214, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 0.0006526315789473684, | |
| "loss": 1.0156, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 0.0006578947368421052, | |
| "loss": 1.2343, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 0.0006631578947368421, | |
| "loss": 1.2906, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.000668421052631579, | |
| "loss": 1.5074, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 0.0006736842105263159, | |
| "loss": 1.0378, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 0.0006789473684210527, | |
| "loss": 1.3764, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 0.0006842105263157895, | |
| "loss": 0.9798, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.0006894736842105264, | |
| "loss": 1.0204, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0006947368421052632, | |
| "loss": 1.0225, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_f1_macro": 0.5685314685314686, | |
| "eval_f1_micro": 0.6923076923076923, | |
| "eval_f1_weighted": 0.6504691889307274, | |
| "eval_loss": 1.1684703826904297, | |
| "eval_precision_macro": 0.5473015873015872, | |
| "eval_precision_micro": 0.6923076923076923, | |
| "eval_precision_weighted": 0.6344322344322344, | |
| "eval_recall_macro": 0.6142857142857142, | |
| "eval_recall_micro": 0.6923076923076923, | |
| "eval_recall_weighted": 0.6923076923076923, | |
| "eval_runtime": 0.0989, | |
| "eval_samples_per_second": 394.464, | |
| "eval_steps_per_second": 30.343, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.0007000000000000001, | |
| "loss": 0.8319, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.0007052631578947369, | |
| "loss": 1.0276, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 0.0007105263157894737, | |
| "loss": 0.9607, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.0007157894736842105, | |
| "loss": 1.2387, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.0007210526315789474, | |
| "loss": 1.2796, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 0.0007263157894736843, | |
| "loss": 0.7215, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.0007315789473684211, | |
| "loss": 1.0518, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0007368421052631579, | |
| "loss": 0.7813, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.0007421052631578947, | |
| "loss": 1.0502, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.0007473684210526316, | |
| "loss": 1.378, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.0007526315789473685, | |
| "loss": 1.2363, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.0007526315789473685, | |
| "loss": 1.4102, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 0.0007578947368421053, | |
| "loss": 0.8184, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.0007631578947368421, | |
| "loss": 1.0921, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.0007684210526315789, | |
| "loss": 0.7126, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.0007736842105263159, | |
| "loss": 1.0646, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 0.0007789473684210527, | |
| "loss": 0.9532, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 0.0007842105263157896, | |
| "loss": 0.7724, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.0007894736842105264, | |
| "loss": 0.8753, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.717948717948718, | |
| "eval_f1_macro": 0.5992857142857144, | |
| "eval_f1_micro": 0.717948717948718, | |
| "eval_f1_weighted": 0.6808608058608059, | |
| "eval_loss": 1.0412697792053223, | |
| "eval_precision_macro": 0.5655555555555555, | |
| "eval_precision_micro": 0.717948717948718, | |
| "eval_precision_weighted": 0.6524216524216524, | |
| "eval_recall_macro": 0.6433333333333333, | |
| "eval_recall_micro": 0.717948717948718, | |
| "eval_recall_weighted": 0.717948717948718, | |
| "eval_runtime": 0.1034, | |
| "eval_samples_per_second": 377.218, | |
| "eval_steps_per_second": 29.017, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 0.0007947368421052632, | |
| "loss": 0.6541, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 0.0008, | |
| "loss": 1.2863, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 0.0008052631578947369, | |
| "loss": 1.0602, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 0.0008105263157894738, | |
| "loss": 1.2225, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 0.0008157894736842106, | |
| "loss": 0.9046, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 0.0008210526315789474, | |
| "loss": 0.6939, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 0.0008263157894736842, | |
| "loss": 0.644, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 0.000831578947368421, | |
| "loss": 0.9403, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 0.000836842105263158, | |
| "loss": 0.5107, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 0.0008421052631578948, | |
| "loss": 1.0886, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 0.0008473684210526316, | |
| "loss": 1.3385, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 0.0008526315789473684, | |
| "loss": 1.2766, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 0.0008578947368421052, | |
| "loss": 0.6848, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 0.0008631578947368422, | |
| "loss": 0.9881, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 0.000868421052631579, | |
| "loss": 0.6309, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 0.0008736842105263158, | |
| "loss": 0.7585, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 0.0008789473684210526, | |
| "loss": 0.6653, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 0.0008842105263157894, | |
| "loss": 1.0764, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.0008894736842105263, | |
| "loss": 0.6241, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7435897435897436, | |
| "eval_f1_macro": 0.6221158958001063, | |
| "eval_f1_micro": 0.7435897435897437, | |
| "eval_f1_weighted": 0.7144862934336619, | |
| "eval_loss": 0.9631038308143616, | |
| "eval_precision_macro": 0.6077777777777779, | |
| "eval_precision_micro": 0.7435897435897436, | |
| "eval_precision_weighted": 0.7235042735042736, | |
| "eval_recall_macro": 0.6766666666666666, | |
| "eval_recall_micro": 0.7435897435897436, | |
| "eval_recall_weighted": 0.7435897435897436, | |
| "eval_runtime": 0.1019, | |
| "eval_samples_per_second": 382.713, | |
| "eval_steps_per_second": 29.439, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 0.0008947368421052632, | |
| "loss": 0.6013, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 0.0009, | |
| "loss": 0.8411, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 0.0009052631578947368, | |
| "loss": 0.9775, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 0.0009105263157894736, | |
| "loss": 0.9363, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 0.0009157894736842105, | |
| "loss": 0.348, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 0.0009210526315789473, | |
| "loss": 0.7705, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 0.0009263157894736844, | |
| "loss": 0.7397, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 0.0009315789473684212, | |
| "loss": 0.3971, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 0.000936842105263158, | |
| "loss": 1.4934, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 0.0009421052631578948, | |
| "loss": 1.2191, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 0.0009473684210526316, | |
| "loss": 1.3495, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 0.0009526315789473686, | |
| "loss": 1.2079, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.0009578947368421054, | |
| "loss": 0.9686, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 0.0009631578947368422, | |
| "loss": 1.6675, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 0.000968421052631579, | |
| "loss": 0.7272, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0009736842105263158, | |
| "loss": 0.563, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.0009789473684210528, | |
| "loss": 1.2433, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.0009842105263157895, | |
| "loss": 1.353, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0009894736842105264, | |
| "loss": 0.5994, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.717948717948718, | |
| "eval_f1_macro": 0.608552036199095, | |
| "eval_f1_micro": 0.717948717948718, | |
| "eval_f1_weighted": 0.6738484743009631, | |
| "eval_loss": 0.8072579503059387, | |
| "eval_precision_macro": 0.5864285714285714, | |
| "eval_precision_micro": 0.717948717948718, | |
| "eval_precision_weighted": 0.6695970695970695, | |
| "eval_recall_macro": 0.6633333333333333, | |
| "eval_recall_micro": 0.717948717948718, | |
| "eval_recall_weighted": 0.717948717948718, | |
| "eval_runtime": 0.1002, | |
| "eval_samples_per_second": 389.316, | |
| "eval_steps_per_second": 29.947, | |
| "step": 190 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5000, | |
| "save_steps": 500, | |
| "total_flos": 3.228625190633472e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |