Training in progress, step 100
Browse files- .gitignore +1 -0
- checkpoint-600/config.json +0 -38
- checkpoint-600/optimizer.pt +0 -3
- checkpoint-600/preprocessor_config.json +0 -22
- checkpoint-600/pytorch_model.bin +0 -3
- checkpoint-600/trainer_state.json +0 -430
- config.json +1 -1
- pytorch_model.bin +1 -1
- runs/Feb24_15-21-30_27e8a3adc154/events.out.tfevents.1677254593.27e8a3adc154.110.2 +2 -2
- checkpoint-600/scheduler.pt → runs/Feb24_17-46-12_27e8a3adc154/1677260784.3715985/events.out.tfevents.1677260784.27e8a3adc154.110.5 +2 -2
- checkpoint-600/scaler.pt → runs/Feb24_17-46-12_27e8a3adc154/events.out.tfevents.1677260784.27e8a3adc154.110.4 +2 -2
- checkpoint-600/training_args.bin → runs/Feb24_17-52-22_27e8a3adc154/1677261159.8668275/events.out.tfevents.1677261159.27e8a3adc154.110.7 +2 -2
- checkpoint-600/rng_state.pth → runs/Feb24_17-52-22_27e8a3adc154/events.out.tfevents.1677261159.27e8a3adc154.110.6 +2 -2
- training_args.bin +1 -1
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
checkpoint-600/config.json
DELETED
|
@@ -1,38 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"ViTForImageClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.0,
|
| 7 |
-
"encoder_stride": 16,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.0,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "0",
|
| 13 |
-
"1": "1",
|
| 14 |
-
"2": "2",
|
| 15 |
-
"3": "3",
|
| 16 |
-
"4": "4"
|
| 17 |
-
},
|
| 18 |
-
"image_size": 224,
|
| 19 |
-
"initializer_range": 0.02,
|
| 20 |
-
"intermediate_size": 3072,
|
| 21 |
-
"label2id": {
|
| 22 |
-
"0": "0",
|
| 23 |
-
"1": "1",
|
| 24 |
-
"2": "2",
|
| 25 |
-
"3": "3",
|
| 26 |
-
"4": "4"
|
| 27 |
-
},
|
| 28 |
-
"layer_norm_eps": 1e-12,
|
| 29 |
-
"model_type": "vit",
|
| 30 |
-
"num_attention_heads": 12,
|
| 31 |
-
"num_channels": 3,
|
| 32 |
-
"num_hidden_layers": 12,
|
| 33 |
-
"patch_size": 16,
|
| 34 |
-
"problem_type": "single_label_classification",
|
| 35 |
-
"qkv_bias": true,
|
| 36 |
-
"torch_dtype": "float32",
|
| 37 |
-
"transformers_version": "4.26.1"
|
| 38 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-600/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:33a722383d4ffcd7da7445ebc6b7efb316dd3c0fadc74a3d83b8f1a07cfd6d40
|
| 3 |
-
size 686537349
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-600/preprocessor_config.json
DELETED
|
@@ -1,22 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_normalize": true,
|
| 3 |
-
"do_rescale": true,
|
| 4 |
-
"do_resize": true,
|
| 5 |
-
"image_mean": [
|
| 6 |
-
0.5,
|
| 7 |
-
0.5,
|
| 8 |
-
0.5
|
| 9 |
-
],
|
| 10 |
-
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
-
"image_std": [
|
| 12 |
-
0.5,
|
| 13 |
-
0.5,
|
| 14 |
-
0.5
|
| 15 |
-
],
|
| 16 |
-
"resample": 2,
|
| 17 |
-
"rescale_factor": 0.00392156862745098,
|
| 18 |
-
"size": {
|
| 19 |
-
"height": 224,
|
| 20 |
-
"width": 224
|
| 21 |
-
}
|
| 22 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-600/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5cd8865690927931e71e4fe5f7cd1c001f5e3c322f7cfe9c0e0faabaf2e20126
|
| 3 |
-
size 343277933
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-600/trainer_state.json
DELETED
|
@@ -1,430 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": 0.7260138988494873,
|
| 3 |
-
"best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-600",
|
| 4 |
-
"epoch": 2.843601895734597,
|
| 5 |
-
"global_step": 600,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.05,
|
| 12 |
-
"learning_rate": 0.00019763033175355452,
|
| 13 |
-
"loss": 1.4193,
|
| 14 |
-
"step": 10
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.09,
|
| 18 |
-
"learning_rate": 0.000195260663507109,
|
| 19 |
-
"loss": 1.0491,
|
| 20 |
-
"step": 20
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.14,
|
| 24 |
-
"learning_rate": 0.00019289099526066352,
|
| 25 |
-
"loss": 1.1612,
|
| 26 |
-
"step": 30
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.19,
|
| 30 |
-
"learning_rate": 0.000190521327014218,
|
| 31 |
-
"loss": 1.0393,
|
| 32 |
-
"step": 40
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.24,
|
| 36 |
-
"learning_rate": 0.00018815165876777252,
|
| 37 |
-
"loss": 1.0533,
|
| 38 |
-
"step": 50
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.28,
|
| 42 |
-
"learning_rate": 0.00018578199052132703,
|
| 43 |
-
"loss": 0.9506,
|
| 44 |
-
"step": 60
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.33,
|
| 48 |
-
"learning_rate": 0.00018341232227488152,
|
| 49 |
-
"loss": 0.9148,
|
| 50 |
-
"step": 70
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.38,
|
| 54 |
-
"learning_rate": 0.00018104265402843603,
|
| 55 |
-
"loss": 0.9735,
|
| 56 |
-
"step": 80
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.43,
|
| 60 |
-
"learning_rate": 0.00017890995260663508,
|
| 61 |
-
"loss": 0.783,
|
| 62 |
-
"step": 90
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.47,
|
| 66 |
-
"learning_rate": 0.0001765402843601896,
|
| 67 |
-
"loss": 0.9235,
|
| 68 |
-
"step": 100
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.47,
|
| 72 |
-
"eval_accuracy": 0.6492890995260664,
|
| 73 |
-
"eval_loss": 0.8972262740135193,
|
| 74 |
-
"eval_runtime": 90.3527,
|
| 75 |
-
"eval_samples_per_second": 9.341,
|
| 76 |
-
"eval_steps_per_second": 1.173,
|
| 77 |
-
"step": 100
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"epoch": 0.52,
|
| 81 |
-
"learning_rate": 0.00017417061611374408,
|
| 82 |
-
"loss": 0.9931,
|
| 83 |
-
"step": 110
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 0.57,
|
| 87 |
-
"learning_rate": 0.0001718009478672986,
|
| 88 |
-
"loss": 1.0035,
|
| 89 |
-
"step": 120
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 0.62,
|
| 93 |
-
"learning_rate": 0.00016943127962085308,
|
| 94 |
-
"loss": 0.9619,
|
| 95 |
-
"step": 130
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 0.66,
|
| 99 |
-
"learning_rate": 0.0001670616113744076,
|
| 100 |
-
"loss": 0.8618,
|
| 101 |
-
"step": 140
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.71,
|
| 105 |
-
"learning_rate": 0.0001646919431279621,
|
| 106 |
-
"loss": 0.9862,
|
| 107 |
-
"step": 150
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.76,
|
| 111 |
-
"learning_rate": 0.0001623222748815166,
|
| 112 |
-
"loss": 0.9977,
|
| 113 |
-
"step": 160
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 0.81,
|
| 117 |
-
"learning_rate": 0.0001599526066350711,
|
| 118 |
-
"loss": 0.8715,
|
| 119 |
-
"step": 170
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 0.85,
|
| 123 |
-
"learning_rate": 0.0001575829383886256,
|
| 124 |
-
"loss": 0.9153,
|
| 125 |
-
"step": 180
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 0.9,
|
| 129 |
-
"learning_rate": 0.0001552132701421801,
|
| 130 |
-
"loss": 0.784,
|
| 131 |
-
"step": 190
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 0.95,
|
| 135 |
-
"learning_rate": 0.00015284360189573462,
|
| 136 |
-
"loss": 0.9253,
|
| 137 |
-
"step": 200
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 0.95,
|
| 141 |
-
"eval_accuracy": 0.6635071090047393,
|
| 142 |
-
"eval_loss": 0.9150586128234863,
|
| 143 |
-
"eval_runtime": 91.0647,
|
| 144 |
-
"eval_samples_per_second": 9.268,
|
| 145 |
-
"eval_steps_per_second": 1.164,
|
| 146 |
-
"step": 200
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 1.0,
|
| 150 |
-
"learning_rate": 0.0001504739336492891,
|
| 151 |
-
"loss": 0.8305,
|
| 152 |
-
"step": 210
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 1.04,
|
| 156 |
-
"learning_rate": 0.0001481042654028436,
|
| 157 |
-
"loss": 0.8379,
|
| 158 |
-
"step": 220
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 1.09,
|
| 162 |
-
"learning_rate": 0.0001457345971563981,
|
| 163 |
-
"loss": 0.707,
|
| 164 |
-
"step": 230
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 1.14,
|
| 168 |
-
"learning_rate": 0.0001433649289099526,
|
| 169 |
-
"loss": 0.8205,
|
| 170 |
-
"step": 240
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 1.18,
|
| 174 |
-
"learning_rate": 0.00014099526066350712,
|
| 175 |
-
"loss": 0.7565,
|
| 176 |
-
"step": 250
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 1.23,
|
| 180 |
-
"learning_rate": 0.0001386255924170616,
|
| 181 |
-
"loss": 0.7539,
|
| 182 |
-
"step": 260
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 1.28,
|
| 186 |
-
"learning_rate": 0.00013625592417061612,
|
| 187 |
-
"loss": 0.9389,
|
| 188 |
-
"step": 270
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 1.33,
|
| 192 |
-
"learning_rate": 0.0001338862559241706,
|
| 193 |
-
"loss": 0.8062,
|
| 194 |
-
"step": 280
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 1.37,
|
| 198 |
-
"learning_rate": 0.00013151658767772512,
|
| 199 |
-
"loss": 0.7702,
|
| 200 |
-
"step": 290
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 1.42,
|
| 204 |
-
"learning_rate": 0.00012914691943127963,
|
| 205 |
-
"loss": 0.8371,
|
| 206 |
-
"step": 300
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 1.42,
|
| 210 |
-
"eval_accuracy": 0.693127962085308,
|
| 211 |
-
"eval_loss": 0.8071145415306091,
|
| 212 |
-
"eval_runtime": 87.0572,
|
| 213 |
-
"eval_samples_per_second": 9.695,
|
| 214 |
-
"eval_steps_per_second": 1.218,
|
| 215 |
-
"step": 300
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 1.47,
|
| 219 |
-
"learning_rate": 0.00012677725118483412,
|
| 220 |
-
"loss": 0.7698,
|
| 221 |
-
"step": 310
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 1.52,
|
| 225 |
-
"learning_rate": 0.00012440758293838863,
|
| 226 |
-
"loss": 0.8412,
|
| 227 |
-
"step": 320
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 1.56,
|
| 231 |
-
"learning_rate": 0.00012203791469194314,
|
| 232 |
-
"loss": 0.8268,
|
| 233 |
-
"step": 330
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.61,
|
| 237 |
-
"learning_rate": 0.00011966824644549763,
|
| 238 |
-
"loss": 0.6359,
|
| 239 |
-
"step": 340
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 1.66,
|
| 243 |
-
"learning_rate": 0.00011729857819905214,
|
| 244 |
-
"loss": 0.6765,
|
| 245 |
-
"step": 350
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 1.71,
|
| 249 |
-
"learning_rate": 0.00011492890995260664,
|
| 250 |
-
"loss": 0.7455,
|
| 251 |
-
"step": 360
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 1.75,
|
| 255 |
-
"learning_rate": 0.00011255924170616114,
|
| 256 |
-
"loss": 0.7108,
|
| 257 |
-
"step": 370
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 1.8,
|
| 261 |
-
"learning_rate": 0.00011018957345971565,
|
| 262 |
-
"loss": 0.6456,
|
| 263 |
-
"step": 380
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 1.85,
|
| 267 |
-
"learning_rate": 0.00010781990521327015,
|
| 268 |
-
"loss": 0.7036,
|
| 269 |
-
"step": 390
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 1.9,
|
| 273 |
-
"learning_rate": 0.00010545023696682465,
|
| 274 |
-
"loss": 0.7355,
|
| 275 |
-
"step": 400
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 1.9,
|
| 279 |
-
"eval_accuracy": 0.707345971563981,
|
| 280 |
-
"eval_loss": 0.7562642693519592,
|
| 281 |
-
"eval_runtime": 87.3813,
|
| 282 |
-
"eval_samples_per_second": 9.659,
|
| 283 |
-
"eval_steps_per_second": 1.213,
|
| 284 |
-
"step": 400
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 1.94,
|
| 288 |
-
"learning_rate": 0.00010308056872037915,
|
| 289 |
-
"loss": 0.6315,
|
| 290 |
-
"step": 410
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 1.99,
|
| 294 |
-
"learning_rate": 0.00010071090047393366,
|
| 295 |
-
"loss": 0.6996,
|
| 296 |
-
"step": 420
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 2.04,
|
| 300 |
-
"learning_rate": 9.834123222748816e-05,
|
| 301 |
-
"loss": 0.6379,
|
| 302 |
-
"step": 430
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 2.09,
|
| 306 |
-
"learning_rate": 9.597156398104266e-05,
|
| 307 |
-
"loss": 0.5765,
|
| 308 |
-
"step": 440
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.13,
|
| 312 |
-
"learning_rate": 9.360189573459716e-05,
|
| 313 |
-
"loss": 0.6309,
|
| 314 |
-
"step": 450
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 2.18,
|
| 318 |
-
"learning_rate": 9.123222748815167e-05,
|
| 319 |
-
"loss": 0.5836,
|
| 320 |
-
"step": 460
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 2.23,
|
| 324 |
-
"learning_rate": 8.886255924170617e-05,
|
| 325 |
-
"loss": 0.5075,
|
| 326 |
-
"step": 470
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 2.27,
|
| 330 |
-
"learning_rate": 8.649289099526067e-05,
|
| 331 |
-
"loss": 0.5817,
|
| 332 |
-
"step": 480
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 2.32,
|
| 336 |
-
"learning_rate": 8.412322274881517e-05,
|
| 337 |
-
"loss": 0.6765,
|
| 338 |
-
"step": 490
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 2.37,
|
| 342 |
-
"learning_rate": 8.175355450236967e-05,
|
| 343 |
-
"loss": 0.6532,
|
| 344 |
-
"step": 500
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 2.37,
|
| 348 |
-
"eval_accuracy": 0.6895734597156398,
|
| 349 |
-
"eval_loss": 0.7542913556098938,
|
| 350 |
-
"eval_runtime": 87.8093,
|
| 351 |
-
"eval_samples_per_second": 9.612,
|
| 352 |
-
"eval_steps_per_second": 1.207,
|
| 353 |
-
"step": 500
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 2.42,
|
| 357 |
-
"learning_rate": 7.938388625592418e-05,
|
| 358 |
-
"loss": 0.5203,
|
| 359 |
-
"step": 510
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 2.46,
|
| 363 |
-
"learning_rate": 7.701421800947868e-05,
|
| 364 |
-
"loss": 0.4772,
|
| 365 |
-
"step": 520
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"epoch": 2.51,
|
| 369 |
-
"learning_rate": 7.464454976303318e-05,
|
| 370 |
-
"loss": 0.6391,
|
| 371 |
-
"step": 530
|
| 372 |
-
},
|
| 373 |
-
{
|
| 374 |
-
"epoch": 2.56,
|
| 375 |
-
"learning_rate": 7.227488151658768e-05,
|
| 376 |
-
"loss": 0.5908,
|
| 377 |
-
"step": 540
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 2.61,
|
| 381 |
-
"learning_rate": 6.990521327014218e-05,
|
| 382 |
-
"loss": 0.5459,
|
| 383 |
-
"step": 550
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 2.65,
|
| 387 |
-
"learning_rate": 6.753554502369669e-05,
|
| 388 |
-
"loss": 0.6922,
|
| 389 |
-
"step": 560
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 2.7,
|
| 393 |
-
"learning_rate": 6.516587677725119e-05,
|
| 394 |
-
"loss": 0.5738,
|
| 395 |
-
"step": 570
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 2.75,
|
| 399 |
-
"learning_rate": 6.279620853080569e-05,
|
| 400 |
-
"loss": 0.5743,
|
| 401 |
-
"step": 580
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 2.8,
|
| 405 |
-
"learning_rate": 6.0426540284360186e-05,
|
| 406 |
-
"loss": 0.5733,
|
| 407 |
-
"step": 590
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 2.84,
|
| 411 |
-
"learning_rate": 5.829383886255925e-05,
|
| 412 |
-
"loss": 0.5982,
|
| 413 |
-
"step": 600
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 2.84,
|
| 417 |
-
"eval_accuracy": 0.726303317535545,
|
| 418 |
-
"eval_loss": 0.7260138988494873,
|
| 419 |
-
"eval_runtime": 88.3787,
|
| 420 |
-
"eval_samples_per_second": 9.55,
|
| 421 |
-
"eval_steps_per_second": 1.199,
|
| 422 |
-
"step": 600
|
| 423 |
-
}
|
| 424 |
-
],
|
| 425 |
-
"max_steps": 844,
|
| 426 |
-
"num_train_epochs": 4,
|
| 427 |
-
"total_flos": 7.422382333315031e+17,
|
| 428 |
-
"trial_name": null,
|
| 429 |
-
"trial_params": null
|
| 430 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Kontawat/vit-diabetic-retinopathy-classification",
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343277933
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f671fb9125ad425a0ecb7b5db622fe1ceb6b4cb2195ee819a5d62cd5b8dfe19e
|
| 3 |
size 343277933
|
runs/Feb24_15-21-30_27e8a3adc154/events.out.tfevents.1677254593.27e8a3adc154.110.2
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:cc9f05b1385e7f8c2b04ce7d23873fb75f65b428616ca6366f49708b72a1747b
|
| 3 |
+
size 4309
|
checkpoint-600/scheduler.pt → runs/Feb24_17-46-12_27e8a3adc154/1677260784.3715985/events.out.tfevents.1677260784.27e8a3adc154.110.5
RENAMED
|
@@ -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 sha256:95056ff28bd5eeab63c82411eef888962410db290faf672323833c607f85a5bd
|
| 3 |
+
size 5749
|
checkpoint-600/scaler.pt → runs/Feb24_17-46-12_27e8a3adc154/events.out.tfevents.1677260784.27e8a3adc154.110.4
RENAMED
|
@@ -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:cf4819bccce9d1f7c9e789c43a21538dcb14a4834d5b44fea459db9bf972f8e0
|
| 3 |
+
size 5909
|
checkpoint-600/training_args.bin → runs/Feb24_17-52-22_27e8a3adc154/1677261159.8668275/events.out.tfevents.1677261159.27e8a3adc154.110.7
RENAMED
|
@@ -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 sha256:568ad8ce7d94a3794f12f0e6463bc623d414ef91951de1603c27a6c39b20d5c2
|
| 3 |
+
size 5749
|
checkpoint-600/rng_state.pth → runs/Feb24_17-52-22_27e8a3adc154/events.out.tfevents.1677261159.27e8a3adc154.110.6
RENAMED
|
@@ -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 sha256:59f2c7494f39669a0e04b5b28cf546a657df815e8428083b7ee59c4dbf51edde
|
| 3 |
+
size 5908
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3515
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74526426310e4bab458ac87d1a1e61d8efd32e55d38c685281cbb869bf97947f
|
| 3 |
size 3515
|