File size: 5,989 Bytes
1c0d312 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 |
{
"best_metric": 0.910958904109589,
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-rim_one-new/checkpoint-30",
"epoch": 19.727272727272727,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.73,
"eval_accuracy": 0.4794520547945205,
"eval_loss": 0.6921706199645996,
"eval_runtime": 25.0333,
"eval_samples_per_second": 5.832,
"eval_steps_per_second": 0.2,
"step": 2
},
{
"epoch": 1.73,
"eval_accuracy": 0.6506849315068494,
"eval_loss": 0.7311218976974487,
"eval_runtime": 4.1824,
"eval_samples_per_second": 34.909,
"eval_steps_per_second": 1.195,
"step": 4
},
{
"epoch": 2.73,
"eval_accuracy": 0.4178082191780822,
"eval_loss": 0.9364489316940308,
"eval_runtime": 4.1884,
"eval_samples_per_second": 34.858,
"eval_steps_per_second": 1.194,
"step": 6
},
{
"epoch": 3.73,
"eval_accuracy": 0.7945205479452054,
"eval_loss": 0.4742239713668823,
"eval_runtime": 4.2915,
"eval_samples_per_second": 34.021,
"eval_steps_per_second": 1.165,
"step": 8
},
{
"epoch": 4.73,
"learning_rate": 8.333333333333334e-05,
"loss": 0.8198,
"step": 10
},
{
"epoch": 4.73,
"eval_accuracy": 0.8561643835616438,
"eval_loss": 0.36144283413887024,
"eval_runtime": 4.4462,
"eval_samples_per_second": 32.837,
"eval_steps_per_second": 1.125,
"step": 10
},
{
"epoch": 5.73,
"eval_accuracy": 0.8561643835616438,
"eval_loss": 0.3010813593864441,
"eval_runtime": 4.3245,
"eval_samples_per_second": 33.761,
"eval_steps_per_second": 1.156,
"step": 12
},
{
"epoch": 6.73,
"eval_accuracy": 0.8561643835616438,
"eval_loss": 0.2709261178970337,
"eval_runtime": 4.3245,
"eval_samples_per_second": 33.761,
"eval_steps_per_second": 1.156,
"step": 14
},
{
"epoch": 7.73,
"eval_accuracy": 0.6027397260273972,
"eval_loss": 0.7967002987861633,
"eval_runtime": 4.3664,
"eval_samples_per_second": 33.437,
"eval_steps_per_second": 1.145,
"step": 16
},
{
"epoch": 8.73,
"eval_accuracy": 0.8287671232876712,
"eval_loss": 0.39434078335762024,
"eval_runtime": 4.348,
"eval_samples_per_second": 33.578,
"eval_steps_per_second": 1.15,
"step": 18
},
{
"epoch": 9.73,
"learning_rate": 5.555555555555556e-05,
"loss": 0.5673,
"step": 20
},
{
"epoch": 9.73,
"eval_accuracy": 0.8835616438356164,
"eval_loss": 0.2661159336566925,
"eval_runtime": 4.3636,
"eval_samples_per_second": 33.458,
"eval_steps_per_second": 1.146,
"step": 20
},
{
"epoch": 10.73,
"eval_accuracy": 0.7671232876712328,
"eval_loss": 0.4626728296279907,
"eval_runtime": 4.4331,
"eval_samples_per_second": 32.934,
"eval_steps_per_second": 1.128,
"step": 22
},
{
"epoch": 11.73,
"eval_accuracy": 0.8835616438356164,
"eval_loss": 0.24509218335151672,
"eval_runtime": 4.4007,
"eval_samples_per_second": 33.177,
"eval_steps_per_second": 1.136,
"step": 24
},
{
"epoch": 12.73,
"eval_accuracy": 0.9041095890410958,
"eval_loss": 0.23970794677734375,
"eval_runtime": 4.1384,
"eval_samples_per_second": 35.279,
"eval_steps_per_second": 1.208,
"step": 26
},
{
"epoch": 13.73,
"eval_accuracy": 0.8904109589041096,
"eval_loss": 0.24433596432209015,
"eval_runtime": 4.1349,
"eval_samples_per_second": 35.309,
"eval_steps_per_second": 1.209,
"step": 28
},
{
"epoch": 14.73,
"learning_rate": 2.777777777777778e-05,
"loss": 0.2571,
"step": 30
},
{
"epoch": 14.73,
"eval_accuracy": 0.910958904109589,
"eval_loss": 0.24097245931625366,
"eval_runtime": 4.2188,
"eval_samples_per_second": 34.607,
"eval_steps_per_second": 1.185,
"step": 30
},
{
"epoch": 15.73,
"eval_accuracy": 0.8904109589041096,
"eval_loss": 0.2714996933937073,
"eval_runtime": 4.1836,
"eval_samples_per_second": 34.898,
"eval_steps_per_second": 1.195,
"step": 32
},
{
"epoch": 16.73,
"eval_accuracy": 0.9041095890410958,
"eval_loss": 0.2597528100013733,
"eval_runtime": 4.1231,
"eval_samples_per_second": 35.41,
"eval_steps_per_second": 1.213,
"step": 34
},
{
"epoch": 17.73,
"eval_accuracy": 0.8972602739726028,
"eval_loss": 0.25846657156944275,
"eval_runtime": 4.1153,
"eval_samples_per_second": 35.477,
"eval_steps_per_second": 1.215,
"step": 36
},
{
"epoch": 18.73,
"eval_accuracy": 0.910958904109589,
"eval_loss": 0.2306668758392334,
"eval_runtime": 4.1812,
"eval_samples_per_second": 34.919,
"eval_steps_per_second": 1.196,
"step": 38
},
{
"epoch": 19.73,
"learning_rate": 0.0,
"loss": 0.1015,
"step": 40
},
{
"epoch": 19.73,
"eval_accuracy": 0.8972602739726028,
"eval_loss": 0.2697519063949585,
"eval_runtime": 4.1223,
"eval_samples_per_second": 35.417,
"eval_steps_per_second": 1.213,
"step": 40
},
{
"epoch": 19.73,
"step": 40,
"total_flos": 5.187420432666501e+17,
"train_loss": 0.4364403486251831,
"train_runtime": 567.1784,
"train_samples_per_second": 11.954,
"train_steps_per_second": 0.071
}
],
"max_steps": 40,
"num_train_epochs": 20,
"total_flos": 5.187420432666501e+17,
"trial_name": null,
"trial_params": null
}
|