File size: 4,200 Bytes
7195d1b 2777c69 7195d1b 2777c69 7195d1b 2777c69 7195d1b 2777c69 7195d1b 2777c69 7195d1b 2777c69 7195d1b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 |
{
"best_metric": 0.5771955847740173,
"best_model_checkpoint": "hBERTv2_mrpc/checkpoint-45",
"epoch": 8.0,
"global_step": 120,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 4.906666666666667e-05,
"loss": 0.6388,
"step": 15
},
{
"epoch": 1.0,
"eval_accuracy": 0.6838235294117647,
"eval_combined_score": 0.7480253018237863,
"eval_f1": 0.8122270742358079,
"eval_loss": 0.6297235488891602,
"eval_runtime": 0.4865,
"eval_samples_per_second": 838.69,
"eval_steps_per_second": 4.111,
"step": 15
},
{
"epoch": 2.0,
"learning_rate": 4.806666666666667e-05,
"loss": 0.612,
"step": 30
},
{
"epoch": 2.0,
"eval_accuracy": 0.6887254901960784,
"eval_combined_score": 0.7511175174915782,
"eval_f1": 0.8135095447870779,
"eval_loss": 0.631518542766571,
"eval_runtime": 0.4865,
"eval_samples_per_second": 838.716,
"eval_steps_per_second": 4.111,
"step": 30
},
{
"epoch": 3.0,
"learning_rate": 4.706666666666667e-05,
"loss": 0.5725,
"step": 45
},
{
"epoch": 3.0,
"eval_accuracy": 0.6936274509803921,
"eval_combined_score": 0.7511016274810076,
"eval_f1": 0.8085758039816232,
"eval_loss": 0.5771955847740173,
"eval_runtime": 0.485,
"eval_samples_per_second": 841.168,
"eval_steps_per_second": 4.123,
"step": 45
},
{
"epoch": 4.0,
"learning_rate": 4.606666666666667e-05,
"loss": 0.512,
"step": 60
},
{
"epoch": 4.0,
"eval_accuracy": 0.7009803921568627,
"eval_combined_score": 0.7580659536541889,
"eval_f1": 0.8151515151515151,
"eval_loss": 0.6260703206062317,
"eval_runtime": 0.4844,
"eval_samples_per_second": 842.253,
"eval_steps_per_second": 4.129,
"step": 60
},
{
"epoch": 5.0,
"learning_rate": 4.5066666666666667e-05,
"loss": 0.3924,
"step": 75
},
{
"epoch": 5.0,
"eval_accuracy": 0.7279411764705882,
"eval_combined_score": 0.7737266857962697,
"eval_f1": 0.8195121951219512,
"eval_loss": 0.6433467268943787,
"eval_runtime": 0.484,
"eval_samples_per_second": 842.954,
"eval_steps_per_second": 4.132,
"step": 75
},
{
"epoch": 6.0,
"learning_rate": 4.406666666666667e-05,
"loss": 0.2592,
"step": 90
},
{
"epoch": 6.0,
"eval_accuracy": 0.6862745098039216,
"eval_combined_score": 0.7228365030222615,
"eval_f1": 0.7593984962406015,
"eval_loss": 0.7530680894851685,
"eval_runtime": 0.4824,
"eval_samples_per_second": 845.726,
"eval_steps_per_second": 4.146,
"step": 90
},
{
"epoch": 7.0,
"learning_rate": 4.3066666666666665e-05,
"loss": 0.1689,
"step": 105
},
{
"epoch": 7.0,
"eval_accuracy": 0.7377450980392157,
"eval_combined_score": 0.7767899328406062,
"eval_f1": 0.8158347676419966,
"eval_loss": 0.7904398441314697,
"eval_runtime": 0.4836,
"eval_samples_per_second": 843.759,
"eval_steps_per_second": 4.136,
"step": 105
},
{
"epoch": 8.0,
"learning_rate": 4.206666666666667e-05,
"loss": 0.1292,
"step": 120
},
{
"epoch": 8.0,
"eval_accuracy": 0.7622549019607843,
"eval_combined_score": 0.8001591705129464,
"eval_f1": 0.8380634390651085,
"eval_loss": 0.9954336285591125,
"eval_runtime": 0.4861,
"eval_samples_per_second": 839.39,
"eval_steps_per_second": 4.115,
"step": 120
},
{
"epoch": 8.0,
"step": 120,
"total_flos": 3654895836069888.0,
"train_loss": 0.18271473944187164,
"train_runtime": 94.8977,
"train_samples_per_second": 1932.608,
"train_steps_per_second": 7.903
}
],
"max_steps": 750,
"num_train_epochs": 50,
"total_flos": 3654895836069888.0,
"trial_name": null,
"trial_params": null
}
|