File size: 3,172 Bytes
bbb25db |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 |
{
"best_metric": 0.6305641531944275,
"best_model_checkpoint": "hBERTv2_new_pretrain_48_KD_w_init_qnli/checkpoint-1638",
"epoch": 7.0,
"global_step": 5733,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 3.9200000000000004e-05,
"loss": 0.6733,
"step": 819
},
{
"epoch": 1.0,
"eval_accuracy": 0.5912502288120081,
"eval_loss": 0.6642831563949585,
"eval_runtime": 11.4659,
"eval_samples_per_second": 476.455,
"eval_steps_per_second": 3.75,
"step": 819
},
{
"epoch": 2.0,
"learning_rate": 3.8400000000000005e-05,
"loss": 0.641,
"step": 1638
},
{
"epoch": 2.0,
"eval_accuracy": 0.6417719201903715,
"eval_loss": 0.6305641531944275,
"eval_runtime": 11.4569,
"eval_samples_per_second": 476.832,
"eval_steps_per_second": 3.753,
"step": 1638
},
{
"epoch": 3.0,
"learning_rate": 3.76e-05,
"loss": 0.5952,
"step": 2457
},
{
"epoch": 3.0,
"eval_accuracy": 0.6377448288486179,
"eval_loss": 0.6487901210784912,
"eval_runtime": 11.4643,
"eval_samples_per_second": 476.521,
"eval_steps_per_second": 3.751,
"step": 2457
},
{
"epoch": 4.0,
"learning_rate": 3.680000000000001e-05,
"loss": 0.5439,
"step": 3276
},
{
"epoch": 4.0,
"eval_accuracy": 0.6302397949844408,
"eval_loss": 0.6660674810409546,
"eval_runtime": 11.4595,
"eval_samples_per_second": 476.722,
"eval_steps_per_second": 3.752,
"step": 3276
},
{
"epoch": 5.0,
"learning_rate": 3.6e-05,
"loss": 0.4907,
"step": 4095
},
{
"epoch": 5.0,
"eval_accuracy": 0.6252974556104705,
"eval_loss": 0.6936535239219666,
"eval_runtime": 11.4579,
"eval_samples_per_second": 476.79,
"eval_steps_per_second": 3.753,
"step": 4095
},
{
"epoch": 6.0,
"learning_rate": 3.52e-05,
"loss": 0.4364,
"step": 4914
},
{
"epoch": 6.0,
"eval_accuracy": 0.6296906461651107,
"eval_loss": 0.7380545139312744,
"eval_runtime": 11.4626,
"eval_samples_per_second": 476.593,
"eval_steps_per_second": 3.751,
"step": 4914
},
{
"epoch": 7.0,
"learning_rate": 3.44e-05,
"loss": 0.3825,
"step": 5733
},
{
"epoch": 7.0,
"eval_accuracy": 0.624016108365367,
"eval_loss": 0.8474876880645752,
"eval_runtime": 11.4645,
"eval_samples_per_second": 476.514,
"eval_steps_per_second": 3.751,
"step": 5733
},
{
"epoch": 7.0,
"step": 5733,
"total_flos": 1.0729602688011469e+17,
"train_loss": 0.5375828685590823,
"train_runtime": 4891.2045,
"train_samples_per_second": 1070.728,
"train_steps_per_second": 8.372
}
],
"max_steps": 40950,
"num_train_epochs": 50,
"total_flos": 1.0729602688011469e+17,
"trial_name": null,
"trial_params": null
}
|