File size: 5,326 Bytes
c1a4df8 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 |
{
"best_metric": 0.8346379647749511,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-864",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 864,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.8633686304092407,
"learning_rate": 0.00011164310281576651,
"loss": 0.584,
"step": 96
},
{
"epoch": 1.0,
"eval_accuracy": 0.7690802348336595,
"eval_f1": 0.7993197278911565,
"eval_loss": 0.48832422494888306,
"eval_precision": 0.706766917293233,
"eval_recall": 0.9197651663405088,
"eval_runtime": 28.3969,
"eval_samples_per_second": 35.99,
"eval_steps_per_second": 1.127,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 1.9557557106018066,
"learning_rate": 9.76877149637957e-05,
"loss": 0.4827,
"step": 192
},
{
"epoch": 2.0,
"eval_accuracy": 0.8003913894324853,
"eval_f1": 0.8222996515679443,
"eval_loss": 0.44451940059661865,
"eval_precision": 0.7409733124018838,
"eval_recall": 0.923679060665362,
"eval_runtime": 28.5294,
"eval_samples_per_second": 35.823,
"eval_steps_per_second": 1.122,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 3.0629470348358154,
"learning_rate": 8.373232711182488e-05,
"loss": 0.448,
"step": 288
},
{
"epoch": 3.0,
"eval_accuracy": 0.824853228962818,
"eval_f1": 0.8353265869365226,
"eval_loss": 0.4216720759868622,
"eval_precision": 0.7881944444444444,
"eval_recall": 0.8884540117416829,
"eval_runtime": 28.7944,
"eval_samples_per_second": 35.493,
"eval_steps_per_second": 1.111,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 5.688210964202881,
"learning_rate": 6.977693925985407e-05,
"loss": 0.4341,
"step": 384
},
{
"epoch": 4.0,
"eval_accuracy": 0.8209393346379648,
"eval_f1": 0.825214899713467,
"eval_loss": 0.42298367619514465,
"eval_precision": 0.8059701492537313,
"eval_recall": 0.8454011741682974,
"eval_runtime": 28.2399,
"eval_samples_per_second": 36.19,
"eval_steps_per_second": 1.133,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 2.334526300430298,
"learning_rate": 5.5821551407883254e-05,
"loss": 0.4202,
"step": 480
},
{
"epoch": 5.0,
"eval_accuracy": 0.8287671232876712,
"eval_f1": 0.8436103663985702,
"eval_loss": 0.4076910614967346,
"eval_precision": 0.7763157894736842,
"eval_recall": 0.923679060665362,
"eval_runtime": 28.534,
"eval_samples_per_second": 35.817,
"eval_steps_per_second": 1.121,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 4.195997714996338,
"learning_rate": 4.186616355591244e-05,
"loss": 0.4109,
"step": 576
},
{
"epoch": 6.0,
"eval_accuracy": 0.8258317025440313,
"eval_f1": 0.842756183745583,
"eval_loss": 0.4115942418575287,
"eval_precision": 0.7681159420289855,
"eval_recall": 0.9334637964774951,
"eval_runtime": 28.3073,
"eval_samples_per_second": 36.104,
"eval_steps_per_second": 1.13,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 2.727288007736206,
"learning_rate": 2.7910775703941627e-05,
"loss": 0.4017,
"step": 672
},
{
"epoch": 7.0,
"eval_accuracy": 0.8307240704500979,
"eval_f1": 0.8467670504871568,
"eval_loss": 0.41019657254219055,
"eval_precision": 0.7734627831715211,
"eval_recall": 0.9354207436399217,
"eval_runtime": 28.5087,
"eval_samples_per_second": 35.849,
"eval_steps_per_second": 1.122,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 3.721353530883789,
"learning_rate": 1.3955387851970814e-05,
"loss": 0.4014,
"step": 768
},
{
"epoch": 8.0,
"eval_accuracy": 0.8258317025440313,
"eval_f1": 0.8405017921146953,
"eval_loss": 0.40405774116516113,
"eval_precision": 0.775206611570248,
"eval_recall": 0.9178082191780822,
"eval_runtime": 28.5925,
"eval_samples_per_second": 35.744,
"eval_steps_per_second": 1.119,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 2.3781871795654297,
"learning_rate": 0.0,
"loss": 0.3968,
"step": 864
},
{
"epoch": 9.0,
"eval_accuracy": 0.8346379647749511,
"eval_f1": 0.8456621004566209,
"eval_loss": 0.4000749886035919,
"eval_precision": 0.7928082191780822,
"eval_recall": 0.9060665362035225,
"eval_runtime": 28.358,
"eval_samples_per_second": 36.039,
"eval_steps_per_second": 1.128,
"step": 864
}
],
"logging_steps": 500,
"max_steps": 864,
"num_input_tokens_seen": 0,
"num_train_epochs": 9,
"save_steps": 500,
"total_flos": 2121256775520.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.8898885181069172,
"learning_rate": 0.00012559849066773733,
"num_train_epochs": 9,
"temperature": 3
}
}
|