File size: 3,401 Bytes
3d9b717 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
{
"best_metric": 0.4296023125768376,
"best_model_checkpoint": "bart-large/checkpoint-2569",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 5138,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.19,
"learning_rate": 4.967886337096146e-05,
"loss": 2.0273,
"step": 500
},
{
"epoch": 0.39,
"learning_rate": 4.9354482937589206e-05,
"loss": 1.4983,
"step": 1000
},
{
"epoch": 0.58,
"learning_rate": 4.903140002595043e-05,
"loss": 1.4727,
"step": 1500
},
{
"epoch": 0.78,
"learning_rate": 4.870701959257818e-05,
"loss": 1.3945,
"step": 2000
},
{
"epoch": 0.97,
"learning_rate": 4.8383287920072665e-05,
"loss": 1.1685,
"step": 2500
},
{
"epoch": 1.0,
"eval_accuracy": 0.6847405112316034,
"eval_f1_macro": 0.4296023125768376,
"eval_f1_micro": 0.6847405112316034,
"eval_f1_weighted": 0.6471198955620663,
"eval_loss": 1.258675456047058,
"eval_macro_fpr": 0.03310536835500512,
"eval_macro_sensitivity": 0.47197476920519743,
"eval_macro_specificity": 0.9759825618150952,
"eval_precision": 0.6359796796355663,
"eval_precision_macro": 0.4175869918662546,
"eval_recall": 0.6847405112316034,
"eval_recall_macro": 0.47197476920519743,
"eval_runtime": 166.2079,
"eval_samples_per_second": 7.767,
"eval_steps_per_second": 3.887,
"eval_weighted_fpr": 0.03183916138621607,
"eval_weighted_sensitivity": 0.6847405112316034,
"eval_weighted_specificity": 0.9549979159948256,
"step": 2569
},
{
"epoch": 1.17,
"learning_rate": 4.80589074867004e-05,
"loss": 1.2814,
"step": 3000
},
{
"epoch": 1.36,
"learning_rate": 4.7734527053328146e-05,
"loss": 1.2579,
"step": 3500
},
{
"epoch": 1.56,
"learning_rate": 4.741079538082263e-05,
"loss": 1.246,
"step": 4000
},
{
"epoch": 1.75,
"learning_rate": 4.708641494745037e-05,
"loss": 1.0685,
"step": 4500
},
{
"epoch": 1.95,
"learning_rate": 4.676203451407811e-05,
"loss": 1.1965,
"step": 5000
},
{
"epoch": 2.0,
"eval_accuracy": 0.6638264910921766,
"eval_f1_macro": 0.3954707529203812,
"eval_f1_micro": 0.6638264910921766,
"eval_f1_weighted": 0.6467821848395333,
"eval_loss": 1.1623183488845825,
"eval_macro_fpr": 0.03422706134984445,
"eval_macro_sensitivity": 0.4261017849773373,
"eval_macro_specificity": 0.9752839802406176,
"eval_precision": 0.6943370263824146,
"eval_precision_macro": 0.45636498568634104,
"eval_recall": 0.6638264910921766,
"eval_recall_macro": 0.4261017849773373,
"eval_runtime": 320.2013,
"eval_samples_per_second": 4.032,
"eval_steps_per_second": 2.017,
"eval_weighted_fpr": 0.03490990990990991,
"eval_weighted_sensitivity": 0.6638264910921766,
"eval_weighted_specificity": 0.9654332125170877,
"step": 5138
}
],
"logging_steps": 500,
"max_steps": 77070,
"num_train_epochs": 30,
"save_steps": 500,
"total_flos": 1.1168202440134656e+16,
"trial_name": null,
"trial_params": null
}
|