Commit ·
b85f93f
1
Parent(s): 8a9f02d
End of training
Browse files- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +334 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6505,
|
| 4 |
+
"eval_loss": 1.5247734785079956,
|
| 5 |
+
"eval_runtime": 210.7248,
|
| 6 |
+
"eval_samples_per_second": 9.491,
|
| 7 |
+
"eval_steps_per_second": 0.299,
|
| 8 |
+
"train_loss": 2.6032654142580958,
|
| 9 |
+
"train_runtime": 22914.0929,
|
| 10 |
+
"train_samples_per_second": 2.646,
|
| 11 |
+
"train_steps_per_second": 0.021
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6505,
|
| 4 |
+
"eval_loss": 1.5247734785079956,
|
| 5 |
+
"eval_runtime": 210.7248,
|
| 6 |
+
"eval_samples_per_second": 9.491,
|
| 7 |
+
"eval_steps_per_second": 0.299
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.6032654142580958,
|
| 4 |
+
"train_runtime": 22914.0929,
|
| 5 |
+
"train_samples_per_second": 2.646,
|
| 6 |
+
"train_steps_per_second": 0.021
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6505,
|
| 3 |
+
"best_model_checkpoint": "huggingface_swinv2/results/checkpoint-474",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 474,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 13 |
+
"loss": 6.9591,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 19 |
+
"loss": 6.2275,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.19,
|
| 24 |
+
"learning_rate": 3.125e-05,
|
| 25 |
+
"loss": 5.4598,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.25,
|
| 30 |
+
"learning_rate": 4.166666666666667e-05,
|
| 31 |
+
"loss": 5.0493,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.32,
|
| 36 |
+
"learning_rate": 4.976525821596245e-05,
|
| 37 |
+
"loss": 4.441,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.38,
|
| 42 |
+
"learning_rate": 4.8591549295774653e-05,
|
| 43 |
+
"loss": 4.2344,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.44,
|
| 48 |
+
"learning_rate": 4.741784037558686e-05,
|
| 49 |
+
"loss": 3.9691,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.51,
|
| 54 |
+
"learning_rate": 4.624413145539906e-05,
|
| 55 |
+
"loss": 3.7754,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.57,
|
| 60 |
+
"learning_rate": 4.507042253521127e-05,
|
| 61 |
+
"loss": 3.5397,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.63,
|
| 66 |
+
"learning_rate": 4.389671361502348e-05,
|
| 67 |
+
"loss": 3.6703,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.7,
|
| 72 |
+
"learning_rate": 4.2723004694835684e-05,
|
| 73 |
+
"loss": 3.3699,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.76,
|
| 78 |
+
"learning_rate": 4.154929577464789e-05,
|
| 79 |
+
"loss": 3.1505,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.82,
|
| 84 |
+
"learning_rate": 4.037558685446009e-05,
|
| 85 |
+
"loss": 3.163,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.89,
|
| 90 |
+
"learning_rate": 3.9201877934272305e-05,
|
| 91 |
+
"loss": 2.9571,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.95,
|
| 96 |
+
"learning_rate": 3.802816901408451e-05,
|
| 97 |
+
"loss": 2.8495,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.0,
|
| 102 |
+
"eval_accuracy": 0.5525,
|
| 103 |
+
"eval_loss": 2.3313448429107666,
|
| 104 |
+
"eval_runtime": 296.5387,
|
| 105 |
+
"eval_samples_per_second": 6.744,
|
| 106 |
+
"eval_steps_per_second": 0.212,
|
| 107 |
+
"step": 158
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.01,
|
| 111 |
+
"learning_rate": 3.6854460093896714e-05,
|
| 112 |
+
"loss": 2.7472,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.08,
|
| 117 |
+
"learning_rate": 3.568075117370892e-05,
|
| 118 |
+
"loss": 2.2962,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.14,
|
| 123 |
+
"learning_rate": 3.450704225352113e-05,
|
| 124 |
+
"loss": 2.3374,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.2,
|
| 129 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 130 |
+
"loss": 2.3174,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.27,
|
| 135 |
+
"learning_rate": 3.215962441314554e-05,
|
| 136 |
+
"loss": 2.3778,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.33,
|
| 141 |
+
"learning_rate": 3.0985915492957744e-05,
|
| 142 |
+
"loss": 2.1876,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.39,
|
| 147 |
+
"learning_rate": 2.9812206572769952e-05,
|
| 148 |
+
"loss": 2.2015,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.46,
|
| 153 |
+
"learning_rate": 2.8638497652582164e-05,
|
| 154 |
+
"loss": 2.11,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.52,
|
| 159 |
+
"learning_rate": 2.746478873239437e-05,
|
| 160 |
+
"loss": 2.0703,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.58,
|
| 165 |
+
"learning_rate": 2.6291079812206577e-05,
|
| 166 |
+
"loss": 2.0761,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.65,
|
| 171 |
+
"learning_rate": 2.511737089201878e-05,
|
| 172 |
+
"loss": 1.925,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.71,
|
| 177 |
+
"learning_rate": 2.3943661971830986e-05,
|
| 178 |
+
"loss": 1.9786,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.77,
|
| 183 |
+
"learning_rate": 2.2769953051643194e-05,
|
| 184 |
+
"loss": 2.0874,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.84,
|
| 189 |
+
"learning_rate": 2.1596244131455402e-05,
|
| 190 |
+
"loss": 1.9243,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.9,
|
| 195 |
+
"learning_rate": 2.0422535211267607e-05,
|
| 196 |
+
"loss": 1.907,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.96,
|
| 201 |
+
"learning_rate": 1.9248826291079812e-05,
|
| 202 |
+
"loss": 1.8825,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.0,
|
| 207 |
+
"eval_accuracy": 0.623,
|
| 208 |
+
"eval_loss": 1.6814827919006348,
|
| 209 |
+
"eval_runtime": 239.2713,
|
| 210 |
+
"eval_samples_per_second": 8.359,
|
| 211 |
+
"eval_steps_per_second": 0.263,
|
| 212 |
+
"step": 316
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.03,
|
| 216 |
+
"learning_rate": 1.807511737089202e-05,
|
| 217 |
+
"loss": 1.8254,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.09,
|
| 222 |
+
"learning_rate": 1.6901408450704224e-05,
|
| 223 |
+
"loss": 1.7649,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.15,
|
| 228 |
+
"learning_rate": 1.5727699530516433e-05,
|
| 229 |
+
"loss": 1.5449,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.22,
|
| 234 |
+
"learning_rate": 1.4553990610328639e-05,
|
| 235 |
+
"loss": 1.5033,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.28,
|
| 240 |
+
"learning_rate": 1.3380281690140845e-05,
|
| 241 |
+
"loss": 1.7012,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.34,
|
| 246 |
+
"learning_rate": 1.2206572769953052e-05,
|
| 247 |
+
"loss": 1.6202,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.41,
|
| 252 |
+
"learning_rate": 1.1032863849765258e-05,
|
| 253 |
+
"loss": 1.6755,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.47,
|
| 258 |
+
"learning_rate": 9.859154929577465e-06,
|
| 259 |
+
"loss": 1.6227,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.53,
|
| 264 |
+
"learning_rate": 8.685446009389673e-06,
|
| 265 |
+
"loss": 1.5438,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.59,
|
| 270 |
+
"learning_rate": 7.511737089201878e-06,
|
| 271 |
+
"loss": 1.5294,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.66,
|
| 276 |
+
"learning_rate": 6.338028169014085e-06,
|
| 277 |
+
"loss": 1.5591,
|
| 278 |
+
"step": 420
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.72,
|
| 282 |
+
"learning_rate": 5.164319248826292e-06,
|
| 283 |
+
"loss": 1.5766,
|
| 284 |
+
"step": 430
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.78,
|
| 288 |
+
"learning_rate": 3.990610328638498e-06,
|
| 289 |
+
"loss": 1.5316,
|
| 290 |
+
"step": 440
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.85,
|
| 294 |
+
"learning_rate": 2.8169014084507042e-06,
|
| 295 |
+
"loss": 1.6038,
|
| 296 |
+
"step": 450
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.91,
|
| 300 |
+
"learning_rate": 1.643192488262911e-06,
|
| 301 |
+
"loss": 1.4692,
|
| 302 |
+
"step": 460
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.97,
|
| 306 |
+
"learning_rate": 4.694835680751174e-07,
|
| 307 |
+
"loss": 1.4956,
|
| 308 |
+
"step": 470
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.0,
|
| 312 |
+
"eval_accuracy": 0.6505,
|
| 313 |
+
"eval_loss": 1.5247734785079956,
|
| 314 |
+
"eval_runtime": 211.3118,
|
| 315 |
+
"eval_samples_per_second": 9.465,
|
| 316 |
+
"eval_steps_per_second": 0.298,
|
| 317 |
+
"step": 474
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.0,
|
| 321 |
+
"step": 474,
|
| 322 |
+
"total_flos": 7.918476182904914e+18,
|
| 323 |
+
"train_loss": 2.6032654142580958,
|
| 324 |
+
"train_runtime": 22914.0929,
|
| 325 |
+
"train_samples_per_second": 2.646,
|
| 326 |
+
"train_steps_per_second": 0.021
|
| 327 |
+
}
|
| 328 |
+
],
|
| 329 |
+
"max_steps": 474,
|
| 330 |
+
"num_train_epochs": 3,
|
| 331 |
+
"total_flos": 7.918476182904914e+18,
|
| 332 |
+
"trial_name": null,
|
| 333 |
+
"trial_params": null
|
| 334 |
+
}
|