Training in progress, epoch 0
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Jan27_19-39-35_42e93dde8b39/1674848401.7786646/events.out.tfevents.1674848401.42e93dde8b39.23.3 +3 -0
- runs/Jan27_19-39-35_42e93dde8b39/events.out.tfevents.1674848401.42e93dde8b39.23.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +307 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 4.4448666072058e+18,
|
| 4 |
+
"train_loss": 0.8382294273802212,
|
| 5 |
+
"train_runtime": 1432.2878,
|
| 6 |
+
"train_samples_per_second": 40.088,
|
| 7 |
+
"train_steps_per_second": 0.313
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346873835
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8eab27e6ee0e205a3d37ec2484af3fa2e743ee5c9ba67d825decfa8f68ac264
|
| 3 |
size 346873835
|
runs/Jan27_19-39-35_42e93dde8b39/1674848401.7786646/events.out.tfevents.1674848401.42e93dde8b39.23.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ad79fe2de2bddf2d39286a843d43c66fc722d121e31f8119936c7cb18ab823c
|
| 3 |
+
size 5547
|
runs/Jan27_19-39-35_42e93dde8b39/events.out.tfevents.1674848401.42e93dde8b39.23.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59131a84dc332727c95c1addc711476380e15a40e39e486278c77a6353022141
|
| 3 |
+
size 8386
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 4.4448666072058e+18,
|
| 4 |
+
"train_loss": 0.8382294273802212,
|
| 5 |
+
"train_runtime": 1432.2878,
|
| 6 |
+
"train_samples_per_second": 40.088,
|
| 7 |
+
"train_steps_per_second": 0.313
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,307 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7163555307885204,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013CKPlus-7e-05-finetuned-FER2013-7e-05/checkpoint-448",
|
| 4 |
+
"epoch": 1.9977728285077951,
|
| 5 |
+
"global_step": 448,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 13 |
+
"loss": 2.2663,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 3.111111111111111e-05,
|
| 19 |
+
"loss": 1.4061,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.13,
|
| 24 |
+
"learning_rate": 4.666666666666666e-05,
|
| 25 |
+
"loss": 1.0956,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 6.222222222222222e-05,
|
| 31 |
+
"loss": 0.9463,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.22,
|
| 36 |
+
"learning_rate": 6.913151364764267e-05,
|
| 37 |
+
"loss": 0.9247,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.27,
|
| 42 |
+
"learning_rate": 6.739454094292804e-05,
|
| 43 |
+
"loss": 0.9155,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.31,
|
| 48 |
+
"learning_rate": 6.565756823821339e-05,
|
| 49 |
+
"loss": 0.961,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.36,
|
| 54 |
+
"learning_rate": 6.392059553349875e-05,
|
| 55 |
+
"loss": 0.8554,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.4,
|
| 60 |
+
"learning_rate": 6.218362282878411e-05,
|
| 61 |
+
"loss": 0.8865,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.45,
|
| 66 |
+
"learning_rate": 6.044665012406948e-05,
|
| 67 |
+
"loss": 0.8997,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.49,
|
| 72 |
+
"learning_rate": 5.870967741935483e-05,
|
| 73 |
+
"loss": 0.8326,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.53,
|
| 78 |
+
"learning_rate": 5.6972704714640195e-05,
|
| 79 |
+
"loss": 0.8242,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.58,
|
| 84 |
+
"learning_rate": 5.523573200992556e-05,
|
| 85 |
+
"loss": 0.8414,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.62,
|
| 90 |
+
"learning_rate": 5.349875930521091e-05,
|
| 91 |
+
"loss": 0.9069,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.67,
|
| 96 |
+
"learning_rate": 5.1761786600496274e-05,
|
| 97 |
+
"loss": 0.8343,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.71,
|
| 102 |
+
"learning_rate": 5.002481389578163e-05,
|
| 103 |
+
"loss": 0.8758,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.76,
|
| 108 |
+
"learning_rate": 4.828784119106699e-05,
|
| 109 |
+
"loss": 0.8383,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.8,
|
| 114 |
+
"learning_rate": 4.6550868486352347e-05,
|
| 115 |
+
"loss": 0.8009,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.85,
|
| 120 |
+
"learning_rate": 4.4813895781637715e-05,
|
| 121 |
+
"loss": 0.8376,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.89,
|
| 126 |
+
"learning_rate": 4.307692307692308e-05,
|
| 127 |
+
"loss": 0.8311,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.94,
|
| 132 |
+
"learning_rate": 4.133995037220843e-05,
|
| 133 |
+
"loss": 0.8379,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.98,
|
| 138 |
+
"learning_rate": 3.9602977667493794e-05,
|
| 139 |
+
"loss": 0.7751,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.0,
|
| 144 |
+
"eval_accuracy": 0.7018668152688772,
|
| 145 |
+
"eval_loss": 0.8418572545051575,
|
| 146 |
+
"eval_runtime": 69.6719,
|
| 147 |
+
"eval_samples_per_second": 103.026,
|
| 148 |
+
"eval_steps_per_second": 3.229,
|
| 149 |
+
"step": 224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.03,
|
| 153 |
+
"learning_rate": 3.786600496277915e-05,
|
| 154 |
+
"loss": 0.7908,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.07,
|
| 159 |
+
"learning_rate": 3.612903225806451e-05,
|
| 160 |
+
"loss": 0.7292,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.12,
|
| 165 |
+
"learning_rate": 3.4392059553349874e-05,
|
| 166 |
+
"loss": 0.7171,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.16,
|
| 171 |
+
"learning_rate": 3.2655086848635236e-05,
|
| 172 |
+
"loss": 0.7593,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.2,
|
| 177 |
+
"learning_rate": 3.091811414392059e-05,
|
| 178 |
+
"loss": 0.7867,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.25,
|
| 183 |
+
"learning_rate": 2.9181141439205953e-05,
|
| 184 |
+
"loss": 0.7366,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.29,
|
| 189 |
+
"learning_rate": 2.744416873449131e-05,
|
| 190 |
+
"loss": 0.7616,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.34,
|
| 195 |
+
"learning_rate": 2.5707196029776673e-05,
|
| 196 |
+
"loss": 0.7214,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.38,
|
| 201 |
+
"learning_rate": 2.3970223325062032e-05,
|
| 202 |
+
"loss": 0.7406,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.43,
|
| 207 |
+
"learning_rate": 2.2233250620347394e-05,
|
| 208 |
+
"loss": 0.8002,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.47,
|
| 213 |
+
"learning_rate": 2.0496277915632752e-05,
|
| 214 |
+
"loss": 0.6751,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.52,
|
| 219 |
+
"learning_rate": 1.875930521091811e-05,
|
| 220 |
+
"loss": 0.6422,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.56,
|
| 225 |
+
"learning_rate": 1.7022332506203473e-05,
|
| 226 |
+
"loss": 0.7,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.61,
|
| 231 |
+
"learning_rate": 1.528535980148883e-05,
|
| 232 |
+
"loss": 0.6619,
|
| 233 |
+
"step": 360
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.65,
|
| 237 |
+
"learning_rate": 1.3548387096774192e-05,
|
| 238 |
+
"loss": 0.7354,
|
| 239 |
+
"step": 370
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.69,
|
| 243 |
+
"learning_rate": 1.1811414392059554e-05,
|
| 244 |
+
"loss": 0.7434,
|
| 245 |
+
"step": 380
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.74,
|
| 249 |
+
"learning_rate": 1.0074441687344912e-05,
|
| 250 |
+
"loss": 0.7027,
|
| 251 |
+
"step": 390
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.78,
|
| 255 |
+
"learning_rate": 8.337468982630273e-06,
|
| 256 |
+
"loss": 0.6515,
|
| 257 |
+
"step": 400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.83,
|
| 261 |
+
"learning_rate": 6.600496277915632e-06,
|
| 262 |
+
"loss": 0.6646,
|
| 263 |
+
"step": 410
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.87,
|
| 267 |
+
"learning_rate": 4.863523573200992e-06,
|
| 268 |
+
"loss": 0.7407,
|
| 269 |
+
"step": 420
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.92,
|
| 273 |
+
"learning_rate": 3.126550868486352e-06,
|
| 274 |
+
"loss": 0.6654,
|
| 275 |
+
"step": 430
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.96,
|
| 279 |
+
"learning_rate": 1.3895781637717121e-06,
|
| 280 |
+
"loss": 0.6632,
|
| 281 |
+
"step": 440
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.0,
|
| 285 |
+
"eval_accuracy": 0.7163555307885204,
|
| 286 |
+
"eval_loss": 0.8176982402801514,
|
| 287 |
+
"eval_runtime": 62.2895,
|
| 288 |
+
"eval_samples_per_second": 115.236,
|
| 289 |
+
"eval_steps_per_second": 3.612,
|
| 290 |
+
"step": 448
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.0,
|
| 294 |
+
"step": 448,
|
| 295 |
+
"total_flos": 4.4448666072058e+18,
|
| 296 |
+
"train_loss": 0.8382294273802212,
|
| 297 |
+
"train_runtime": 1432.2878,
|
| 298 |
+
"train_samples_per_second": 40.088,
|
| 299 |
+
"train_steps_per_second": 0.313
|
| 300 |
+
}
|
| 301 |
+
],
|
| 302 |
+
"max_steps": 448,
|
| 303 |
+
"num_train_epochs": 2,
|
| 304 |
+
"total_flos": 4.4448666072058e+18,
|
| 305 |
+
"trial_name": null,
|
| 306 |
+
"trial_params": null
|
| 307 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b05cbd883f52dd736b65fdf8b756f87c2d27869768b85175c9119a6e51d92c5
|
| 3 |
size 3439
|