| { | |
| "best_metric": 0.5112138390541077, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-144", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 144, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6931, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.6931, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.6916, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6917, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6899, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.6889, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.96124031007752e-05, | |
| "loss": 0.6856, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.883720930232558e-05, | |
| "loss": 0.6874, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.8062015503875976e-05, | |
| "loss": 0.6862, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.728682170542636e-05, | |
| "loss": 0.6849, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.651162790697675e-05, | |
| "loss": 0.677, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.573643410852713e-05, | |
| "loss": 0.6701, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.496124031007753e-05, | |
| "loss": 0.6784, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.418604651162791e-05, | |
| "loss": 0.6784, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.34108527131783e-05, | |
| "loss": 0.6687, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.263565891472868e-05, | |
| "loss": 0.6648, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.186046511627907e-05, | |
| "loss": 0.6661, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.108527131782946e-05, | |
| "loss": 0.6421, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.0310077519379843e-05, | |
| "loss": 0.6458, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.953488372093023e-05, | |
| "loss": 0.6615, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.875968992248062e-05, | |
| "loss": 0.6294, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.798449612403101e-05, | |
| "loss": 0.6471, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.7209302325581394e-05, | |
| "loss": 0.6923, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.7499999999999999, | |
| "eval_loss": 0.6188636422157288, | |
| "eval_precision": 0.6, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 13.3176, | |
| "eval_samples_per_second": 7.133, | |
| "eval_steps_per_second": 0.451, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.6434108527131784e-05, | |
| "loss": 0.6528, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.565891472868217e-05, | |
| "loss": 0.6468, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.488372093023256e-05, | |
| "loss": 0.6816, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.4108527131782945e-05, | |
| "loss": 0.6155, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6151, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.2558139534883724e-05, | |
| "loss": 0.6055, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.1782945736434114e-05, | |
| "loss": 0.63, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.1007751937984497e-05, | |
| "loss": 0.6136, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.0232558139534883e-05, | |
| "loss": 0.6024, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9457364341085275e-05, | |
| "loss": 0.6039, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.868217054263566e-05, | |
| "loss": 0.6381, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.7906976744186048e-05, | |
| "loss": 0.6171, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.7131782945736434e-05, | |
| "loss": 0.5989, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.6356589147286826e-05, | |
| "loss": 0.6496, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5581395348837212e-05, | |
| "loss": 0.5904, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.48062015503876e-05, | |
| "loss": 0.5641, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.4031007751937988e-05, | |
| "loss": 0.6415, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.3255813953488374e-05, | |
| "loss": 0.5581, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2480620155038764e-05, | |
| "loss": 0.5596, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.170542635658915e-05, | |
| "loss": 0.6017, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.0930232558139536e-05, | |
| "loss": 0.5437, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.0155038759689922e-05, | |
| "loss": 0.5613, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.937984496124031e-05, | |
| "loss": 0.617, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8604651162790697e-05, | |
| "loss": 0.7115, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.7499999999999999, | |
| "eval_loss": 0.5825784206390381, | |
| "eval_precision": 0.6, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 12.6935, | |
| "eval_samples_per_second": 7.484, | |
| "eval_steps_per_second": 0.473, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.7829457364341087e-05, | |
| "loss": 0.6016, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.7054263565891473e-05, | |
| "loss": 0.5401, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.6279069767441862e-05, | |
| "loss": 0.5289, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5503875968992248e-05, | |
| "loss": 0.521, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4728682170542638e-05, | |
| "loss": 0.5441, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.3953488372093024e-05, | |
| "loss": 0.5942, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3178294573643413e-05, | |
| "loss": 0.5576, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.24031007751938e-05, | |
| "loss": 0.5702, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1627906976744187e-05, | |
| "loss": 0.5567, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0852713178294575e-05, | |
| "loss": 0.5222, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.0077519379844961e-05, | |
| "loss": 0.565, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.302325581395349e-06, | |
| "loss": 0.5274, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.527131782945736e-06, | |
| "loss": 0.5156, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.751937984496124e-06, | |
| "loss": 0.562, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.976744186046512e-06, | |
| "loss": 0.5159, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.2015503875969e-06, | |
| "loss": 0.5327, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.426356589147287e-06, | |
| "loss": 0.5364, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.651162790697674e-06, | |
| "loss": 0.5982, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.875968992248062e-06, | |
| "loss": 0.6285, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.10077519379845e-06, | |
| "loss": 0.5116, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.325581395348837e-06, | |
| "loss": 0.5596, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.550387596899225e-06, | |
| "loss": 0.5538, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.751937984496125e-07, | |
| "loss": 0.568, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.5701, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.7499999999999999, | |
| "eval_loss": 0.5112138390541077, | |
| "eval_precision": 0.6, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 11.597, | |
| "eval_samples_per_second": 8.192, | |
| "eval_steps_per_second": 0.517, | |
| "step": 144 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 144, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.401724127688704e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |