Training in progress, epoch 0
Browse files- all_results.json +5 -5
- config.json +16 -14
- model.safetensors +2 -2
- runs/Dec15_01-14-35_ef188d9b7084/events.out.tfevents.1734225287.ef188d9b7084.405.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +79 -372
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 6.666666666666667,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 6.666666666666667,
|
| 3 |
+
"total_flos": 3.032854323351552e+16,
|
| 4 |
+
"train_loss": 1.8625539779663085,
|
| 5 |
+
"train_runtime": 349.1269,
|
| 6 |
+
"train_samples_per_second": 5.213,
|
| 7 |
+
"train_steps_per_second": 0.029
|
| 8 |
}
|
config.json
CHANGED
|
@@ -17,24 +17,26 @@
|
|
| 17 |
"hidden_dropout_prob": 0.0,
|
| 18 |
"hidden_size": 768,
|
| 19 |
"id2label": {
|
| 20 |
-
"0": "
|
| 21 |
-
"1": "
|
| 22 |
-
"2": "
|
| 23 |
-
"3": "
|
| 24 |
-
"4": "
|
| 25 |
-
"5": "
|
| 26 |
-
"6": "
|
|
|
|
| 27 |
},
|
| 28 |
"image_size": 224,
|
| 29 |
"initializer_range": 0.02,
|
| 30 |
"label2id": {
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
|
|
|
| 38 |
},
|
| 39 |
"layer_norm_eps": 1e-05,
|
| 40 |
"mlp_ratio": 4.0,
|
|
|
|
| 17 |
"hidden_dropout_prob": 0.0,
|
| 18 |
"hidden_size": 768,
|
| 19 |
"id2label": {
|
| 20 |
+
"0": "anger",
|
| 21 |
+
"1": "surprise",
|
| 22 |
+
"2": "contempt",
|
| 23 |
+
"3": "happy",
|
| 24 |
+
"4": "neutral",
|
| 25 |
+
"5": "fear",
|
| 26 |
+
"6": "sad",
|
| 27 |
+
"7": "disgust"
|
| 28 |
},
|
| 29 |
"image_size": 224,
|
| 30 |
"initializer_range": 0.02,
|
| 31 |
"label2id": {
|
| 32 |
+
"anger": 0,
|
| 33 |
+
"contempt": 2,
|
| 34 |
+
"disgust": 7,
|
| 35 |
+
"fear": 5,
|
| 36 |
+
"happy": 3,
|
| 37 |
+
"neutral": 4,
|
| 38 |
+
"sad": 6,
|
| 39 |
+
"surprise": 1
|
| 40 |
},
|
| 41 |
"layer_norm_eps": 1e-05,
|
| 42 |
"mlp_ratio": 4.0,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5100a5639b8a67ad81543bb7a1e7e67fdb516e892031d70e1ca0733c7d4e639
|
| 3 |
+
size 110361288
|
runs/Dec15_01-14-35_ef188d9b7084/events.out.tfevents.1734225287.ef188d9b7084.405.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e00bbc475c5b43bcea30e74677d45159a7fce14cc826295142b660eb69436f4
|
| 3 |
+
size 9389
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 6.666666666666667,
|
| 3 |
+
"total_flos": 3.032854323351552e+16,
|
| 4 |
+
"train_loss": 1.8625539779663085,
|
| 5 |
+
"train_runtime": 349.1269,
|
| 6 |
+
"train_samples_per_second": 5.213,
|
| 7 |
+
"train_steps_per_second": 0.029
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,390 +1,97 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch":
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
"epoch": 0.1834862385321101,
|
| 27 |
-
"grad_norm": 15.808608055114746,
|
| 28 |
-
"learning_rate": 3.061224489795919e-05,
|
| 29 |
-
"loss": 1.9515,
|
| 30 |
-
"step": 30
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.24464831804281345,
|
| 34 |
-
"grad_norm": 23.111419677734375,
|
| 35 |
-
"learning_rate": 4.0816326530612245e-05,
|
| 36 |
-
"loss": 1.7452,
|
| 37 |
-
"step": 40
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.3058103975535168,
|
| 41 |
-
"grad_norm": 24.703895568847656,
|
| 42 |
-
"learning_rate": 4.988636363636364e-05,
|
| 43 |
-
"loss": 1.5294,
|
| 44 |
-
"step": 50
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.3669724770642202,
|
| 48 |
-
"grad_norm": 26.341184616088867,
|
| 49 |
-
"learning_rate": 4.875e-05,
|
| 50 |
-
"loss": 1.4046,
|
| 51 |
-
"step": 60
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.42813455657492355,
|
| 55 |
-
"grad_norm": 23.89405059814453,
|
| 56 |
-
"learning_rate": 4.7613636363636367e-05,
|
| 57 |
-
"loss": 1.3451,
|
| 58 |
-
"step": 70
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.4892966360856269,
|
| 62 |
-
"grad_norm": 22.658981323242188,
|
| 63 |
-
"learning_rate": 4.647727272727273e-05,
|
| 64 |
-
"loss": 1.315,
|
| 65 |
-
"step": 80
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.5504587155963303,
|
| 69 |
-
"grad_norm": 32.74925231933594,
|
| 70 |
-
"learning_rate": 4.5340909090909095e-05,
|
| 71 |
-
"loss": 1.3286,
|
| 72 |
-
"step": 90
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.6116207951070336,
|
| 76 |
-
"grad_norm": 34.46269607543945,
|
| 77 |
-
"learning_rate": 4.4204545454545455e-05,
|
| 78 |
-
"loss": 1.253,
|
| 79 |
-
"step": 100
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.672782874617737,
|
| 83 |
-
"grad_norm": 20.414508819580078,
|
| 84 |
-
"learning_rate": 4.3068181818181816e-05,
|
| 85 |
-
"loss": 1.2188,
|
| 86 |
-
"step": 110
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.7339449541284404,
|
| 90 |
-
"grad_norm": 22.735107421875,
|
| 91 |
-
"learning_rate": 4.193181818181818e-05,
|
| 92 |
-
"loss": 1.246,
|
| 93 |
-
"step": 120
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.7951070336391437,
|
| 97 |
-
"grad_norm": 23.86024284362793,
|
| 98 |
-
"learning_rate": 4.079545454545455e-05,
|
| 99 |
-
"loss": 1.1803,
|
| 100 |
-
"step": 130
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.8562691131498471,
|
| 104 |
-
"grad_norm": 34.048885345458984,
|
| 105 |
-
"learning_rate": 3.965909090909091e-05,
|
| 106 |
-
"loss": 1.1822,
|
| 107 |
-
"step": 140
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.9174311926605505,
|
| 111 |
-
"grad_norm": 27.799007415771484,
|
| 112 |
-
"learning_rate": 3.852272727272728e-05,
|
| 113 |
-
"loss": 1.1625,
|
| 114 |
-
"step": 150
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.9785932721712538,
|
| 118 |
-
"grad_norm": 27.95413589477539,
|
| 119 |
-
"learning_rate": 3.738636363636363e-05,
|
| 120 |
-
"loss": 1.1631,
|
| 121 |
-
"step": 160
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.9969418960244648,
|
| 125 |
-
"eval_accuracy": 0.5851979345955249,
|
| 126 |
-
"eval_loss": 1.0535521507263184,
|
| 127 |
-
"eval_runtime": 15.0707,
|
| 128 |
-
"eval_samples_per_second": 154.206,
|
| 129 |
-
"eval_steps_per_second": 4.844,
|
| 130 |
-
"step": 163
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 1.0412844036697249,
|
| 134 |
-
"grad_norm": 24.71836280822754,
|
| 135 |
-
"learning_rate": 3.625e-05,
|
| 136 |
-
"loss": 1.1357,
|
| 137 |
-
"step": 170
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 1.1024464831804281,
|
| 141 |
-
"grad_norm": 22.25391387939453,
|
| 142 |
-
"learning_rate": 3.511363636363637e-05,
|
| 143 |
-
"loss": 1.1481,
|
| 144 |
-
"step": 180
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 1.1636085626911314,
|
| 148 |
-
"grad_norm": 22.642160415649414,
|
| 149 |
-
"learning_rate": 3.397727272727273e-05,
|
| 150 |
-
"loss": 1.1071,
|
| 151 |
-
"step": 190
|
| 152 |
-
},
|
| 153 |
-
{
|
| 154 |
-
"epoch": 1.224770642201835,
|
| 155 |
-
"grad_norm": 23.1135311126709,
|
| 156 |
-
"learning_rate": 3.2840909090909096e-05,
|
| 157 |
-
"loss": 1.1349,
|
| 158 |
-
"step": 200
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 1.2859327217125383,
|
| 162 |
-
"grad_norm": 19.403104782104492,
|
| 163 |
-
"learning_rate": 3.1704545454545456e-05,
|
| 164 |
-
"loss": 1.1109,
|
| 165 |
-
"step": 210
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 1.3470948012232415,
|
| 169 |
-
"grad_norm": 29.44010353088379,
|
| 170 |
-
"learning_rate": 3.056818181818182e-05,
|
| 171 |
-
"loss": 1.1196,
|
| 172 |
-
"step": 220
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 1.408256880733945,
|
| 176 |
-
"grad_norm": 29.79566764831543,
|
| 177 |
-
"learning_rate": 2.943181818181818e-05,
|
| 178 |
-
"loss": 1.0698,
|
| 179 |
-
"step": 230
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 1.4694189602446484,
|
| 183 |
-
"grad_norm": 28.45584487915039,
|
| 184 |
-
"learning_rate": 2.829545454545455e-05,
|
| 185 |
-
"loss": 1.0802,
|
| 186 |
-
"step": 240
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 1.5305810397553516,
|
| 190 |
-
"grad_norm": 22.51582145690918,
|
| 191 |
-
"learning_rate": 2.7159090909090913e-05,
|
| 192 |
-
"loss": 1.1015,
|
| 193 |
-
"step": 250
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 1.591743119266055,
|
| 197 |
-
"grad_norm": 21.58193016052246,
|
| 198 |
-
"learning_rate": 2.6022727272727277e-05,
|
| 199 |
-
"loss": 1.0757,
|
| 200 |
-
"step": 260
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 1.6529051987767585,
|
| 204 |
-
"grad_norm": 17.50481605529785,
|
| 205 |
-
"learning_rate": 2.4886363636363637e-05,
|
| 206 |
-
"loss": 1.0788,
|
| 207 |
-
"step": 270
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 1.7140672782874617,
|
| 211 |
-
"grad_norm": 22.194198608398438,
|
| 212 |
-
"learning_rate": 2.375e-05,
|
| 213 |
-
"loss": 1.0431,
|
| 214 |
-
"step": 280
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 1.7752293577981653,
|
| 218 |
-
"grad_norm": 28.903148651123047,
|
| 219 |
-
"learning_rate": 2.2613636363636365e-05,
|
| 220 |
-
"loss": 1.051,
|
| 221 |
-
"step": 290
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 1.8363914373088686,
|
| 225 |
-
"grad_norm": 19.929737091064453,
|
| 226 |
-
"learning_rate": 2.147727272727273e-05,
|
| 227 |
-
"loss": 1.0269,
|
| 228 |
-
"step": 300
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 1.8975535168195719,
|
| 232 |
-
"grad_norm": 23.347131729125977,
|
| 233 |
-
"learning_rate": 2.034090909090909e-05,
|
| 234 |
-
"loss": 1.0226,
|
| 235 |
-
"step": 310
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 1.9587155963302751,
|
| 239 |
-
"grad_norm": 22.177705764770508,
|
| 240 |
-
"learning_rate": 1.9204545454545454e-05,
|
| 241 |
-
"loss": 1.096,
|
| 242 |
-
"step": 320
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 1.9954128440366974,
|
| 246 |
-
"eval_accuracy": 0.641566265060241,
|
| 247 |
-
"eval_loss": 0.9225364327430725,
|
| 248 |
-
"eval_runtime": 15.4942,
|
| 249 |
-
"eval_samples_per_second": 149.992,
|
| 250 |
-
"eval_steps_per_second": 4.711,
|
| 251 |
-
"step": 326
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 2.021406727828746,
|
| 255 |
-
"grad_norm": 24.717140197753906,
|
| 256 |
-
"learning_rate": 1.806818181818182e-05,
|
| 257 |
-
"loss": 0.9788,
|
| 258 |
-
"step": 330
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 2.0825688073394497,
|
| 262 |
-
"grad_norm": 30.048473358154297,
|
| 263 |
-
"learning_rate": 1.6931818181818182e-05,
|
| 264 |
-
"loss": 1.0206,
|
| 265 |
-
"step": 340
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"epoch": 2.143730886850153,
|
| 269 |
-
"grad_norm": 24.10106086730957,
|
| 270 |
-
"learning_rate": 1.5795454545454546e-05,
|
| 271 |
-
"loss": 0.963,
|
| 272 |
-
"step": 350
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 2.2048929663608563,
|
| 276 |
-
"grad_norm": 26.799161911010742,
|
| 277 |
-
"learning_rate": 1.4659090909090909e-05,
|
| 278 |
-
"loss": 1.0239,
|
| 279 |
-
"step": 360
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 2.2660550458715596,
|
| 283 |
-
"grad_norm": 24.41145896911621,
|
| 284 |
-
"learning_rate": 1.3522727272727273e-05,
|
| 285 |
-
"loss": 0.9914,
|
| 286 |
-
"step": 370
|
| 287 |
-
},
|
| 288 |
-
{
|
| 289 |
-
"epoch": 2.327217125382263,
|
| 290 |
-
"grad_norm": 25.299041748046875,
|
| 291 |
-
"learning_rate": 1.2386363636363638e-05,
|
| 292 |
-
"loss": 1.0049,
|
| 293 |
-
"step": 380
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 2.388379204892966,
|
| 297 |
-
"grad_norm": 20.791305541992188,
|
| 298 |
-
"learning_rate": 1.125e-05,
|
| 299 |
-
"loss": 1.0156,
|
| 300 |
-
"step": 390
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 2.44954128440367,
|
| 304 |
-
"grad_norm": 27.16722297668457,
|
| 305 |
-
"learning_rate": 1.0113636363636365e-05,
|
| 306 |
-
"loss": 1.059,
|
| 307 |
-
"step": 400
|
| 308 |
-
},
|
| 309 |
-
{
|
| 310 |
-
"epoch": 2.510703363914373,
|
| 311 |
-
"grad_norm": 23.442485809326172,
|
| 312 |
-
"learning_rate": 8.977272727272727e-06,
|
| 313 |
-
"loss": 0.9931,
|
| 314 |
-
"step": 410
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 2.5718654434250765,
|
| 318 |
-
"grad_norm": 26.62813377380371,
|
| 319 |
-
"learning_rate": 7.840909090909091e-06,
|
| 320 |
-
"loss": 1.0159,
|
| 321 |
-
"step": 420
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.63302752293578,
|
| 325 |
-
"grad_norm": 19.204635620117188,
|
| 326 |
-
"learning_rate": 6.704545454545455e-06,
|
| 327 |
-
"loss": 1.0279,
|
| 328 |
-
"step": 430
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"epoch": 2.694189602446483,
|
| 332 |
-
"grad_norm": 23.251445770263672,
|
| 333 |
-
"learning_rate": 5.568181818181818e-06,
|
| 334 |
-
"loss": 0.9971,
|
| 335 |
-
"step": 440
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 2.7553516819571864,
|
| 339 |
-
"grad_norm": 25.26046371459961,
|
| 340 |
-
"learning_rate": 4.4318181818181824e-06,
|
| 341 |
-
"loss": 1.0267,
|
| 342 |
-
"step": 450
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 2.81651376146789,
|
| 346 |
-
"grad_norm": 19.80088233947754,
|
| 347 |
-
"learning_rate": 3.295454545454545e-06,
|
| 348 |
-
"loss": 0.9795,
|
| 349 |
-
"step": 460
|
| 350 |
-
},
|
| 351 |
-
{
|
| 352 |
-
"epoch": 2.8776758409785934,
|
| 353 |
-
"grad_norm": 23.87816047668457,
|
| 354 |
-
"learning_rate": 2.1590909090909092e-06,
|
| 355 |
-
"loss": 1.0087,
|
| 356 |
-
"step": 470
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 2.9388379204892967,
|
| 360 |
-
"grad_norm": 21.836708068847656,
|
| 361 |
-
"learning_rate": 1.0227272727272729e-06,
|
| 362 |
-
"loss": 0.9571,
|
| 363 |
-
"step": 480
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 2.99388379204893,
|
| 367 |
-
"eval_accuracy": 0.6587779690189329,
|
| 368 |
-
"eval_loss": 0.8806350827217102,
|
| 369 |
-
"eval_runtime": 16.023,
|
| 370 |
-
"eval_samples_per_second": 145.041,
|
| 371 |
-
"eval_steps_per_second": 4.556,
|
| 372 |
-
"step": 489
|
| 373 |
},
|
| 374 |
{
|
| 375 |
-
"epoch":
|
| 376 |
-
"step":
|
| 377 |
-
"total_flos":
|
| 378 |
-
"train_loss": 1.
|
| 379 |
-
"train_runtime":
|
| 380 |
-
"train_samples_per_second":
|
| 381 |
-
"train_steps_per_second": 0.
|
| 382 |
}
|
| 383 |
],
|
| 384 |
"logging_steps": 10,
|
| 385 |
-
"max_steps":
|
| 386 |
"num_input_tokens_seen": 0,
|
| 387 |
-
"num_train_epochs":
|
| 388 |
"save_steps": 500,
|
| 389 |
"stateful_callbacks": {
|
| 390 |
"TrainerControl": {
|
|
@@ -398,7 +105,7 @@
|
|
| 398 |
"attributes": {}
|
| 399 |
}
|
| 400 |
},
|
| 401 |
-
"total_flos":
|
| 402 |
"train_batch_size": 32,
|
| 403 |
"trial_name": null,
|
| 404 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2857142857142857,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-10",
|
| 4 |
+
"epoch": 6.666666666666667,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 10,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.6666666666666666,
|
| 13 |
+
"eval_accuracy": 0.09523809523809523,
|
| 14 |
+
"eval_loss": 1.8175530433654785,
|
| 15 |
+
"eval_runtime": 18.3681,
|
| 16 |
+
"eval_samples_per_second": 1.143,
|
| 17 |
+
"eval_steps_per_second": 0.054,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.14285714285714285,
|
| 23 |
+
"eval_loss": 1.8961031436920166,
|
| 24 |
+
"eval_runtime": 0.9567,
|
| 25 |
+
"eval_samples_per_second": 21.951,
|
| 26 |
+
"eval_steps_per_second": 1.045,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.6666666666666665,
|
| 31 |
+
"eval_accuracy": 0.14285714285714285,
|
| 32 |
+
"eval_loss": 1.9159153699874878,
|
| 33 |
+
"eval_runtime": 0.9471,
|
| 34 |
+
"eval_samples_per_second": 22.173,
|
| 35 |
+
"eval_steps_per_second": 1.056,
|
| 36 |
+
"step": 4
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.19047619047619047,
|
| 41 |
+
"eval_loss": 1.8906145095825195,
|
| 42 |
+
"eval_runtime": 0.9581,
|
| 43 |
+
"eval_samples_per_second": 21.919,
|
| 44 |
+
"eval_steps_per_second": 1.044,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.666666666666667,
|
| 49 |
+
"eval_accuracy": 0.19047619047619047,
|
| 50 |
+
"eval_loss": 1.8720425367355347,
|
| 51 |
+
"eval_runtime": 1.0672,
|
| 52 |
+
"eval_samples_per_second": 19.678,
|
| 53 |
+
"eval_steps_per_second": 0.937,
|
| 54 |
+
"step": 7
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.19047619047619047,
|
| 59 |
+
"eval_loss": 1.8452097177505493,
|
| 60 |
+
"eval_runtime": 1.0316,
|
| 61 |
+
"eval_samples_per_second": 20.357,
|
| 62 |
+
"eval_steps_per_second": 0.969,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 6.666666666666667,
|
| 67 |
+
"grad_norm": 13.042926788330078,
|
| 68 |
+
"learning_rate": 0.0,
|
| 69 |
+
"loss": 1.8626,
|
| 70 |
"step": 10
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"epoch": 6.666666666666667,
|
| 74 |
+
"eval_accuracy": 0.2857142857142857,
|
| 75 |
+
"eval_loss": 1.8388439416885376,
|
| 76 |
+
"eval_runtime": 1.2038,
|
| 77 |
+
"eval_samples_per_second": 17.445,
|
| 78 |
+
"eval_steps_per_second": 0.831,
|
| 79 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 6.666666666666667,
|
| 83 |
+
"step": 10,
|
| 84 |
+
"total_flos": 3.032854323351552e+16,
|
| 85 |
+
"train_loss": 1.8625539779663085,
|
| 86 |
+
"train_runtime": 349.1269,
|
| 87 |
+
"train_samples_per_second": 5.213,
|
| 88 |
+
"train_steps_per_second": 0.029
|
| 89 |
}
|
| 90 |
],
|
| 91 |
"logging_steps": 10,
|
| 92 |
+
"max_steps": 10,
|
| 93 |
"num_input_tokens_seen": 0,
|
| 94 |
+
"num_train_epochs": 10,
|
| 95 |
"save_steps": 500,
|
| 96 |
"stateful_callbacks": {
|
| 97 |
"TrainerControl": {
|
|
|
|
| 105 |
"attributes": {}
|
| 106 |
}
|
| 107 |
},
|
| 108 |
+
"total_flos": 3.032854323351552e+16,
|
| 109 |
"train_batch_size": 32,
|
| 110 |
"trial_name": null,
|
| 111 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53581cdaaa08f2df72a2c1a9225fbf542987cceb74268d020c6a0047c0fe6214
|
| 3 |
size 5368
|