Upload 14 files
Browse files- README.md +195 -334
- all_results.json +10 -10
- eval_results.json +5 -5
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,46 +3,31 @@ license: apache-2.0
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
-
- name: bart-base-spelling-nl-
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
| 11 |
|
| 12 |
-
|
| 13 |
-
[facebook/bart-base](https://huggingface.co/facebook/bart-base).
|
| 14 |
|
|
|
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss: 0.
|
| 17 |
-
- Cer: 0.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
| 21 |
-
|
| 22 |
-
[facebook/bart-base](https://huggingface.co/facebook/bart-base)
|
| 23 |
-
trained on spelling correction. It leans on the excellent work by
|
| 24 |
-
Oliver Guhr ([github](https://github.com/oliverguhr/spelling),
|
| 25 |
-
[huggingface](https://huggingface.co/oliverguhr/spelling-correction-english-base)). Training
|
| 26 |
-
was performed on an AWS EC2 instance (g5.xlarge) on a single GPU.
|
| 27 |
|
| 28 |
## Intended uses & limitations
|
| 29 |
|
| 30 |
-
|
| 31 |
-
[Valkuil.net](https://valkuil.net) context-sensitive spelling
|
| 32 |
-
checker.
|
| 33 |
|
| 34 |
## Training and evaluation data
|
| 35 |
|
| 36 |
-
|
| 37 |
-
of text from three public Dutch sources, downloaded from the
|
| 38 |
-
[Opus corpus](https://opus.nlpl.eu/):
|
| 39 |
-
|
| 40 |
-
- nl-europarlv7.1m.txt (2,000,000 lines)
|
| 41 |
-
- nl-opensubtitles2016.1m.txt (2,000,000 lines)
|
| 42 |
-
- nl-wikipedia.txt (964,203 lines)
|
| 43 |
-
|
| 44 |
-
Together these texts comprise 73,818,804 tokens.
|
| 45 |
-
|
| 46 |
|
| 47 |
## Training procedure
|
| 48 |
|
|
@@ -63,315 +48,191 @@ The following hyperparameters were used during training:
|
|
| 63 |
|
| 64 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 65 |
|:-------------:|:-----:|:------:|:---------------:|:------:|
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.
|
| 152 |
-
| 0.
|
| 153 |
-
| 0.
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.
|
| 156 |
-
| 0.
|
| 157 |
-
| 0.
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 0.
|
| 163 |
-
| 0.
|
| 164 |
-
| 0.
|
| 165 |
-
| 0.
|
| 166 |
-
| 0.
|
| 167 |
-
| 0.
|
| 168 |
-
| 0.
|
| 169 |
-
| 0.
|
| 170 |
-
| 0.
|
| 171 |
-
| 0.
|
| 172 |
-
| 0.
|
| 173 |
-
| 0.
|
| 174 |
-
| 0.
|
| 175 |
-
| 0.
|
| 176 |
-
| 0.
|
| 177 |
-
| 0.
|
| 178 |
-
| 0.
|
| 179 |
-
| 0.
|
| 180 |
-
| 0.
|
| 181 |
-
| 0.
|
| 182 |
-
| 0.
|
| 183 |
-
| 0.
|
| 184 |
-
| 0.
|
| 185 |
-
| 0.
|
| 186 |
-
| 0.
|
| 187 |
-
| 0.
|
| 188 |
-
| 0.
|
| 189 |
-
| 0.
|
| 190 |
-
| 0.
|
| 191 |
-
| 0.
|
| 192 |
-
| 0.
|
| 193 |
-
| 0.
|
| 194 |
-
| 0.
|
| 195 |
-
| 0.
|
| 196 |
-
| 0.
|
| 197 |
-
| 0.
|
| 198 |
-
| 0.
|
| 199 |
-
| 0.
|
| 200 |
-
| 0.
|
| 201 |
-
| 0.
|
| 202 |
-
| 0.
|
| 203 |
-
| 0.
|
| 204 |
-
| 0.
|
| 205 |
-
| 0.
|
| 206 |
-
| 0.
|
| 207 |
-
| 0.
|
| 208 |
-
| 0.
|
| 209 |
-
| 0.
|
| 210 |
-
| 0.
|
| 211 |
-
| 0.
|
| 212 |
-
| 0.
|
| 213 |
-
| 0.
|
| 214 |
-
| 0.
|
| 215 |
-
| 0.
|
| 216 |
-
| 0.
|
| 217 |
-
| 0.
|
| 218 |
-
| 0.
|
| 219 |
-
| 0.
|
| 220 |
-
| 0.
|
| 221 |
-
| 0.
|
| 222 |
-
| 0.
|
| 223 |
-
| 0.
|
| 224 |
-
| 0.
|
| 225 |
-
| 0.
|
| 226 |
-
| 0.
|
| 227 |
-
| 0.
|
| 228 |
-
| 0.
|
| 229 |
-
| 0.
|
| 230 |
-
| 0.
|
| 231 |
-
| 0.
|
| 232 |
-
| 0.
|
| 233 |
-
| 0.
|
| 234 |
-
| 0.
|
| 235 |
-
| 0.
|
| 236 |
-
| 0.
|
| 237 |
-
| 0.
|
| 238 |
-
| 0.
|
| 239 |
-
| 0.
|
| 240 |
-
| 0.
|
| 241 |
-
| 0.
|
| 242 |
-
| 0.
|
| 243 |
-
| 0.
|
| 244 |
-
| 0.
|
| 245 |
-
| 0.
|
| 246 |
-
| 0.
|
| 247 |
-
| 0.
|
| 248 |
-
| 0.
|
| 249 |
-
| 0.
|
| 250 |
-
| 0.
|
| 251 |
-
| 0.0351 | 1.2 | 186000 | 0.0227 | 0.9199 |
|
| 252 |
-
| 0.0305 | 1.21 | 187000 | 0.0230 | 0.9199 |
|
| 253 |
-
| 0.0376 | 1.21 | 188000 | 0.0228 | 0.9199 |
|
| 254 |
-
| 0.0338 | 1.22 | 189000 | 0.0225 | 0.9200 |
|
| 255 |
-
| 0.0315 | 1.23 | 190000 | 0.0229 | 0.9199 |
|
| 256 |
-
| 0.0369 | 1.23 | 191000 | 0.0229 | 0.9199 |
|
| 257 |
-
| 0.0288 | 1.24 | 192000 | 0.0227 | 0.9199 |
|
| 258 |
-
| 0.0344 | 1.25 | 193000 | 0.0225 | 0.9199 |
|
| 259 |
-
| 0.0283 | 1.25 | 194000 | 0.0221 | 0.9199 |
|
| 260 |
-
| 0.0377 | 1.26 | 195000 | 0.0225 | 0.9198 |
|
| 261 |
-
| 0.0395 | 1.27 | 196000 | 0.0225 | 0.9199 |
|
| 262 |
-
| 0.0268 | 1.27 | 197000 | 0.0224 | 0.9199 |
|
| 263 |
-
| 0.032 | 1.28 | 198000 | 0.0222 | 0.9199 |
|
| 264 |
-
| 0.0328 | 1.28 | 199000 | 0.0221 | 0.9199 |
|
| 265 |
-
| 0.0278 | 1.29 | 200000 | 0.0220 | 0.9198 |
|
| 266 |
-
| 0.029 | 1.3 | 201000 | 0.0221 | 0.9199 |
|
| 267 |
-
| 0.0319 | 1.3 | 202000 | 0.0218 | 0.9199 |
|
| 268 |
-
| 0.0422 | 1.31 | 203000 | 0.0220 | 0.9199 |
|
| 269 |
-
| 0.0301 | 1.32 | 204000 | 0.0215 | 0.9198 |
|
| 270 |
-
| 0.0293 | 1.32 | 205000 | 0.0217 | 0.9198 |
|
| 271 |
-
| 0.0347 | 1.33 | 206000 | 0.0216 | 0.9199 |
|
| 272 |
-
| 0.0288 | 1.34 | 207000 | 0.0215 | 0.9199 |
|
| 273 |
-
| 0.0264 | 1.34 | 208000 | 0.0216 | 0.9199 |
|
| 274 |
-
| 0.0341 | 1.35 | 209000 | 0.0214 | 0.9199 |
|
| 275 |
-
| 0.029 | 1.36 | 210000 | 0.0213 | 0.9199 |
|
| 276 |
-
| 0.0281 | 1.36 | 211000 | 0.0218 | 0.9198 |
|
| 277 |
-
| 0.033 | 1.37 | 212000 | 0.0212 | 0.9199 |
|
| 278 |
-
| 0.0348 | 1.37 | 213000 | 0.0211 | 0.9199 |
|
| 279 |
-
| 0.0291 | 1.38 | 214000 | 0.0214 | 0.9199 |
|
| 280 |
-
| 0.0353 | 1.39 | 215000 | 0.0212 | 0.9199 |
|
| 281 |
-
| 0.0324 | 1.39 | 216000 | 0.0209 | 0.9199 |
|
| 282 |
-
| 0.0342 | 1.4 | 217000 | 0.0209 | 0.9199 |
|
| 283 |
-
| 0.0293 | 1.41 | 218000 | 0.0212 | 0.9199 |
|
| 284 |
-
| 0.0281 | 1.41 | 219000 | 0.0209 | 0.9199 |
|
| 285 |
-
| 0.0286 | 1.42 | 220000 | 0.0209 | 0.9198 |
|
| 286 |
-
| 0.0297 | 1.43 | 221000 | 0.0205 | 0.9200 |
|
| 287 |
-
| 0.0256 | 1.43 | 222000 | 0.0207 | 0.9199 |
|
| 288 |
-
| 0.0261 | 1.44 | 223000 | 0.0209 | 0.9198 |
|
| 289 |
-
| 0.0274 | 1.45 | 224000 | 0.0204 | 0.9199 |
|
| 290 |
-
| 0.0343 | 1.45 | 225000 | 0.0201 | 0.9199 |
|
| 291 |
-
| 0.0249 | 1.46 | 226000 | 0.0204 | 0.9199 |
|
| 292 |
-
| 0.0267 | 1.47 | 227000 | 0.0202 | 0.9199 |
|
| 293 |
-
| 0.0264 | 1.47 | 228000 | 0.0202 | 0.9199 |
|
| 294 |
-
| 0.031 | 1.48 | 229000 | 0.0201 | 0.9199 |
|
| 295 |
-
| 0.0273 | 1.48 | 230000 | 0.0199 | 0.9199 |
|
| 296 |
-
| 0.024 | 1.49 | 231000 | 0.0199 | 0.9199 |
|
| 297 |
-
| 0.0295 | 1.5 | 232000 | 0.0198 | 0.9199 |
|
| 298 |
-
| 0.0281 | 1.5 | 233000 | 0.0196 | 0.9199 |
|
| 299 |
-
| 0.0243 | 1.51 | 234000 | 0.0195 | 0.9198 |
|
| 300 |
-
| 0.0258 | 1.52 | 235000 | 0.0197 | 0.9199 |
|
| 301 |
-
| 0.0272 | 1.52 | 236000 | 0.0196 | 0.9198 |
|
| 302 |
-
| 0.0261 | 1.53 | 237000 | 0.0198 | 0.9199 |
|
| 303 |
-
| 0.0222 | 1.54 | 238000 | 0.0198 | 0.9199 |
|
| 304 |
-
| 0.0259 | 1.54 | 239000 | 0.0195 | 0.9199 |
|
| 305 |
-
| 0.0317 | 1.55 | 240000 | 0.0194 | 0.9199 |
|
| 306 |
-
| 0.0266 | 1.56 | 241000 | 0.0191 | 0.9199 |
|
| 307 |
-
| 0.0272 | 1.56 | 242000 | 0.0193 | 0.9199 |
|
| 308 |
-
| 0.0236 | 1.57 | 243000 | 0.0194 | 0.9199 |
|
| 309 |
-
| 0.0266 | 1.57 | 244000 | 0.0193 | 0.9198 |
|
| 310 |
-
| 0.027 | 1.58 | 245000 | 0.0195 | 0.9199 |
|
| 311 |
-
| 0.0257 | 1.59 | 246000 | 0.0192 | 0.9199 |
|
| 312 |
-
| 0.0276 | 1.59 | 247000 | 0.0190 | 0.9199 |
|
| 313 |
-
| 0.0238 | 1.6 | 248000 | 0.0188 | 0.9199 |
|
| 314 |
-
| 0.0301 | 1.61 | 249000 | 0.0188 | 0.9199 |
|
| 315 |
-
| 0.0273 | 1.61 | 250000 | 0.0189 | 0.9199 |
|
| 316 |
-
| 0.0246 | 1.62 | 251000 | 0.0187 | 0.9198 |
|
| 317 |
-
| 0.0309 | 1.63 | 252000 | 0.0187 | 0.9198 |
|
| 318 |
-
| 0.0237 | 1.63 | 253000 | 0.0188 | 0.9199 |
|
| 319 |
-
| 0.0234 | 1.64 | 254000 | 0.0184 | 0.9198 |
|
| 320 |
-
| 0.0246 | 1.65 | 255000 | 0.0186 | 0.9198 |
|
| 321 |
-
| 0.0213 | 1.65 | 256000 | 0.0182 | 0.9199 |
|
| 322 |
-
| 0.0251 | 1.66 | 257000 | 0.0182 | 0.9198 |
|
| 323 |
-
| 0.0236 | 1.67 | 258000 | 0.0184 | 0.9198 |
|
| 324 |
-
| 0.0276 | 1.67 | 259000 | 0.0185 | 0.9198 |
|
| 325 |
-
| 0.0233 | 1.68 | 260000 | 0.0182 | 0.9199 |
|
| 326 |
-
| 0.0205 | 1.68 | 261000 | 0.0183 | 0.9198 |
|
| 327 |
-
| 0.0253 | 1.69 | 262000 | 0.0181 | 0.9198 |
|
| 328 |
-
| 0.0221 | 1.7 | 263000 | 0.0180 | 0.9198 |
|
| 329 |
-
| 0.0228 | 1.7 | 264000 | 0.0182 | 0.9199 |
|
| 330 |
-
| 0.0209 | 1.71 | 265000 | 0.0181 | 0.9198 |
|
| 331 |
-
| 0.0319 | 1.72 | 266000 | 0.0179 | 0.9199 |
|
| 332 |
-
| 0.0236 | 1.72 | 267000 | 0.0178 | 0.9199 |
|
| 333 |
-
| 0.029 | 1.73 | 268000 | 0.0179 | 0.9198 |
|
| 334 |
-
| 0.0233 | 1.74 | 269000 | 0.0178 | 0.9198 |
|
| 335 |
-
| 0.0248 | 1.74 | 270000 | 0.0176 | 0.9198 |
|
| 336 |
-
| 0.0211 | 1.75 | 271000 | 0.0177 | 0.9198 |
|
| 337 |
-
| 0.0257 | 1.76 | 272000 | 0.0177 | 0.9198 |
|
| 338 |
-
| 0.0247 | 1.76 | 273000 | 0.0175 | 0.9199 |
|
| 339 |
-
| 0.0323 | 1.77 | 274000 | 0.0176 | 0.9199 |
|
| 340 |
-
| 0.0236 | 1.77 | 275000 | 0.0175 | 0.9198 |
|
| 341 |
-
| 0.0202 | 1.78 | 276000 | 0.0176 | 0.9198 |
|
| 342 |
-
| 0.0318 | 1.79 | 277000 | 0.0174 | 0.9199 |
|
| 343 |
-
| 0.0206 | 1.79 | 278000 | 0.0175 | 0.9198 |
|
| 344 |
-
| 0.0245 | 1.8 | 279000 | 0.0174 | 0.9199 |
|
| 345 |
-
| 0.0177 | 1.81 | 280000 | 0.0174 | 0.9199 |
|
| 346 |
-
| 0.0268 | 1.81 | 281000 | 0.0174 | 0.9199 |
|
| 347 |
-
| 0.0209 | 1.82 | 282000 | 0.0172 | 0.9199 |
|
| 348 |
-
| 0.0248 | 1.83 | 283000 | 0.0171 | 0.9198 |
|
| 349 |
-
| 0.0205 | 1.83 | 284000 | 0.0173 | 0.9198 |
|
| 350 |
-
| 0.0231 | 1.84 | 285000 | 0.0172 | 0.9199 |
|
| 351 |
-
| 0.0278 | 1.85 | 286000 | 0.0171 | 0.9198 |
|
| 352 |
-
| 0.0244 | 1.85 | 287000 | 0.0171 | 0.9198 |
|
| 353 |
-
| 0.0223 | 1.86 | 288000 | 0.0169 | 0.9198 |
|
| 354 |
-
| 0.0285 | 1.87 | 289000 | 0.0168 | 0.9198 |
|
| 355 |
-
| 0.0223 | 1.87 | 290000 | 0.0169 | 0.9198 |
|
| 356 |
-
| 0.0231 | 1.88 | 291000 | 0.0169 | 0.9198 |
|
| 357 |
-
| 0.0192 | 1.88 | 292000 | 0.0169 | 0.9198 |
|
| 358 |
-
| 0.0234 | 1.89 | 293000 | 0.0168 | 0.9198 |
|
| 359 |
-
| 0.0223 | 1.9 | 294000 | 0.0168 | 0.9198 |
|
| 360 |
-
| 0.0255 | 1.9 | 295000 | 0.0168 | 0.9198 |
|
| 361 |
-
| 0.0248 | 1.91 | 296000 | 0.0166 | 0.9198 |
|
| 362 |
-
| 0.0216 | 1.92 | 297000 | 0.0166 | 0.9198 |
|
| 363 |
-
| 0.0219 | 1.92 | 298000 | 0.0167 | 0.9198 |
|
| 364 |
-
| 0.0196 | 1.93 | 299000 | 0.0167 | 0.9198 |
|
| 365 |
-
| 0.0175 | 1.94 | 300000 | 0.0166 | 0.9198 |
|
| 366 |
-
| 0.0228 | 1.94 | 301000 | 0.0165 | 0.9198 |
|
| 367 |
-
| 0.019 | 1.95 | 302000 | 0.0165 | 0.9198 |
|
| 368 |
-
| 0.0191 | 1.96 | 303000 | 0.0165 | 0.9198 |
|
| 369 |
-
| 0.0249 | 1.96 | 304000 | 0.0165 | 0.9198 |
|
| 370 |
-
| 0.0233 | 1.97 | 305000 | 0.0164 | 0.9198 |
|
| 371 |
-
| 0.0211 | 1.97 | 306000 | 0.0164 | 0.9198 |
|
| 372 |
-
| 0.02 | 1.98 | 307000 | 0.0164 | 0.9198 |
|
| 373 |
-
| 0.0191 | 1.99 | 308000 | 0.0164 | 0.9198 |
|
| 374 |
-
| 0.0214 | 1.99 | 309000 | 0.0164 | 0.9198 |
|
| 375 |
|
| 376 |
|
| 377 |
### Framework versions
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
+
- name: bart-base-spelling-nl-1m-3
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
+
# bart-base-spelling-nl-1m-3
|
|
|
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.0053
|
| 18 |
+
- Cer: 0.0117
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
| 22 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Intended uses & limitations
|
| 25 |
|
| 26 |
+
More information needed
|
|
|
|
|
|
|
| 27 |
|
| 28 |
## Training and evaluation data
|
| 29 |
|
| 30 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
## Training procedure
|
| 33 |
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 50 |
|:-------------:|:-----:|:------:|:---------------:|:------:|
|
| 51 |
+
| 0.0834 | 0.01 | 1000 | 0.0603 | 0.9216 |
|
| 52 |
+
| 0.0566 | 0.02 | 2000 | 0.0467 | 0.9217 |
|
| 53 |
+
| 0.0534 | 0.03 | 3000 | 0.0436 | 0.9216 |
|
| 54 |
+
| 0.0461 | 0.04 | 4000 | 0.0392 | 0.9216 |
|
| 55 |
+
| 0.0416 | 0.05 | 5000 | 0.0354 | 0.9216 |
|
| 56 |
+
| 0.0433 | 0.06 | 6000 | 0.0336 | 0.9216 |
|
| 57 |
+
| 0.045 | 0.08 | 7000 | 0.0315 | 0.9216 |
|
| 58 |
+
| 0.0452 | 0.09 | 8000 | 0.0305 | 0.9216 |
|
| 59 |
+
| 0.04 | 0.1 | 9000 | 0.0281 | 0.9216 |
|
| 60 |
+
| 0.0307 | 0.11 | 10000 | 0.0273 | 0.9216 |
|
| 61 |
+
| 0.0382 | 0.12 | 11000 | 0.0269 | 0.9216 |
|
| 62 |
+
| 0.036 | 0.13 | 12000 | 0.0254 | 0.9216 |
|
| 63 |
+
| 0.0412 | 0.14 | 13000 | 0.0258 | 0.9216 |
|
| 64 |
+
| 0.0404 | 0.15 | 14000 | 0.0238 | 0.9216 |
|
| 65 |
+
| 0.0265 | 0.16 | 15000 | 0.0239 | 0.9216 |
|
| 66 |
+
| 0.029 | 0.17 | 16000 | 0.0235 | 0.9216 |
|
| 67 |
+
| 0.0295 | 0.18 | 17000 | 0.0218 | 0.9216 |
|
| 68 |
+
| 0.0262 | 0.19 | 18000 | 0.0214 | 0.9216 |
|
| 69 |
+
| 0.0274 | 0.21 | 19000 | 0.0222 | 0.9216 |
|
| 70 |
+
| 0.0317 | 0.22 | 20000 | 0.0204 | 0.9216 |
|
| 71 |
+
| 0.0248 | 0.23 | 21000 | 0.0204 | 0.9216 |
|
| 72 |
+
| 0.0258 | 0.24 | 22000 | 0.0195 | 0.9216 |
|
| 73 |
+
| 0.0247 | 0.25 | 23000 | 0.0188 | 0.9216 |
|
| 74 |
+
| 0.0285 | 0.26 | 24000 | 0.0191 | 0.9215 |
|
| 75 |
+
| 0.031 | 0.27 | 25000 | 0.0192 | 0.9216 |
|
| 76 |
+
| 0.0267 | 0.28 | 26000 | 0.0188 | 0.9216 |
|
| 77 |
+
| 0.0245 | 0.29 | 27000 | 0.0177 | 0.9216 |
|
| 78 |
+
| 0.0258 | 0.3 | 28000 | 0.0177 | 0.9216 |
|
| 79 |
+
| 0.0235 | 0.31 | 29000 | 0.0169 | 0.9216 |
|
| 80 |
+
| 0.0235 | 0.32 | 30000 | 0.0176 | 0.9216 |
|
| 81 |
+
| 0.0223 | 0.34 | 31000 | 0.0165 | 0.9216 |
|
| 82 |
+
| 0.0219 | 0.35 | 32000 | 0.0167 | 0.9216 |
|
| 83 |
+
| 0.0214 | 0.36 | 33000 | 0.0165 | 0.9216 |
|
| 84 |
+
| 0.0232 | 0.37 | 34000 | 0.0163 | 0.9216 |
|
| 85 |
+
| 0.0192 | 0.38 | 35000 | 0.0162 | 0.9216 |
|
| 86 |
+
| 0.0159 | 0.39 | 36000 | 0.0160 | 0.9216 |
|
| 87 |
+
| 0.0205 | 0.4 | 37000 | 0.0150 | 0.9216 |
|
| 88 |
+
| 0.0197 | 0.41 | 38000 | 0.0152 | 0.9216 |
|
| 89 |
+
| 0.0205 | 0.42 | 39000 | 0.0150 | 0.9216 |
|
| 90 |
+
| 0.0182 | 0.43 | 40000 | 0.0145 | 0.9216 |
|
| 91 |
+
| 0.0204 | 0.44 | 41000 | 0.0139 | 0.9216 |
|
| 92 |
+
| 0.0201 | 0.45 | 42000 | 0.0146 | 0.9216 |
|
| 93 |
+
| 0.0202 | 0.46 | 43000 | 0.0132 | 0.9215 |
|
| 94 |
+
| 0.0219 | 0.48 | 44000 | 0.0146 | 0.9216 |
|
| 95 |
+
| 0.0161 | 0.49 | 45000 | 0.0134 | 0.9215 |
|
| 96 |
+
| 0.0172 | 0.5 | 46000 | 0.0137 | 0.9216 |
|
| 97 |
+
| 0.0199 | 0.51 | 47000 | 0.0133 | 0.9215 |
|
| 98 |
+
| 0.0211 | 0.52 | 48000 | 0.0132 | 0.9215 |
|
| 99 |
+
| 0.0184 | 0.53 | 49000 | 0.0136 | 0.9216 |
|
| 100 |
+
| 0.0191 | 0.54 | 50000 | 0.0129 | 0.9216 |
|
| 101 |
+
| 0.017 | 0.55 | 51000 | 0.0127 | 0.9216 |
|
| 102 |
+
| 0.0188 | 0.56 | 52000 | 0.0127 | 0.9215 |
|
| 103 |
+
| 0.0157 | 0.57 | 53000 | 0.0128 | 0.9216 |
|
| 104 |
+
| 0.0158 | 0.58 | 54000 | 0.0127 | 0.9216 |
|
| 105 |
+
| 0.0145 | 0.59 | 55000 | 0.0117 | 0.9216 |
|
| 106 |
+
| 0.0148 | 0.61 | 56000 | 0.0123 | 0.9216 |
|
| 107 |
+
| 0.0153 | 0.62 | 57000 | 0.0115 | 0.9216 |
|
| 108 |
+
| 0.0182 | 0.63 | 58000 | 0.0115 | 0.9216 |
|
| 109 |
+
| 0.0178 | 0.64 | 59000 | 0.0112 | 0.9215 |
|
| 110 |
+
| 0.0187 | 0.65 | 60000 | 0.0113 | 0.9215 |
|
| 111 |
+
| 0.0174 | 0.66 | 61000 | 0.0119 | 0.9216 |
|
| 112 |
+
| 0.0135 | 0.67 | 62000 | 0.0115 | 0.9215 |
|
| 113 |
+
| 0.0167 | 0.68 | 63000 | 0.0112 | 0.9216 |
|
| 114 |
+
| 0.0163 | 0.69 | 64000 | 0.0111 | 0.9215 |
|
| 115 |
+
| 0.0128 | 0.7 | 65000 | 0.0110 | 0.9215 |
|
| 116 |
+
| 0.0178 | 0.71 | 66000 | 0.0113 | 0.9215 |
|
| 117 |
+
| 0.0142 | 0.72 | 67000 | 0.0110 | 0.9215 |
|
| 118 |
+
| 0.0143 | 0.74 | 68000 | 0.0110 | 0.9215 |
|
| 119 |
+
| 0.0168 | 0.75 | 69000 | 0.0106 | 0.9216 |
|
| 120 |
+
| 0.0136 | 0.76 | 70000 | 0.0107 | 0.9215 |
|
| 121 |
+
| 0.0141 | 0.77 | 71000 | 0.0104 | 0.9215 |
|
| 122 |
+
| 0.0217 | 0.78 | 72000 | 0.0115 | 0.9216 |
|
| 123 |
+
| 0.012 | 0.79 | 73000 | 0.0105 | 0.9215 |
|
| 124 |
+
| 0.0141 | 0.8 | 74000 | 0.0100 | 0.9215 |
|
| 125 |
+
| 0.0136 | 0.81 | 75000 | 0.0096 | 0.9215 |
|
| 126 |
+
| 0.0106 | 0.82 | 76000 | 0.0104 | 0.9216 |
|
| 127 |
+
| 0.0176 | 0.83 | 77000 | 0.0102 | 0.9216 |
|
| 128 |
+
| 0.0169 | 0.84 | 78000 | 0.0099 | 0.9215 |
|
| 129 |
+
| 0.0118 | 0.85 | 79000 | 0.0102 | 0.9215 |
|
| 130 |
+
| 0.0178 | 0.86 | 80000 | 0.0095 | 0.9215 |
|
| 131 |
+
| 0.0145 | 0.88 | 81000 | 0.0097 | 0.9216 |
|
| 132 |
+
| 0.0154 | 0.89 | 82000 | 0.0099 | 0.9215 |
|
| 133 |
+
| 0.0129 | 0.9 | 83000 | 0.0094 | 0.9215 |
|
| 134 |
+
| 0.0125 | 0.91 | 84000 | 0.0097 | 0.9215 |
|
| 135 |
+
| 0.0147 | 0.92 | 85000 | 0.0093 | 0.9215 |
|
| 136 |
+
| 0.0145 | 0.93 | 86000 | 0.0091 | 0.9215 |
|
| 137 |
+
| 0.0121 | 0.94 | 87000 | 0.0089 | 0.9215 |
|
| 138 |
+
| 0.0125 | 0.95 | 88000 | 0.0094 | 0.9215 |
|
| 139 |
+
| 0.0113 | 0.96 | 89000 | 0.0088 | 0.9216 |
|
| 140 |
+
| 0.0098 | 0.97 | 90000 | 0.0094 | 0.9216 |
|
| 141 |
+
| 0.0137 | 0.98 | 91000 | 0.0089 | 0.9215 |
|
| 142 |
+
| 0.0105 | 0.99 | 92000 | 0.0091 | 0.9215 |
|
| 143 |
+
| 0.01 | 1.01 | 93000 | 0.0090 | 0.9216 |
|
| 144 |
+
| 0.0103 | 1.02 | 94000 | 0.0087 | 0.9216 |
|
| 145 |
+
| 0.0103 | 1.03 | 95000 | 0.0091 | 0.9215 |
|
| 146 |
+
| 0.0107 | 1.04 | 96000 | 0.0088 | 0.9216 |
|
| 147 |
+
| 0.0109 | 1.05 | 97000 | 0.0087 | 0.9215 |
|
| 148 |
+
| 0.0102 | 1.06 | 98000 | 0.0090 | 0.9216 |
|
| 149 |
+
| 0.0109 | 1.07 | 99000 | 0.0087 | 0.9215 |
|
| 150 |
+
| 0.0094 | 1.08 | 100000 | 0.0084 | 0.9215 |
|
| 151 |
+
| 0.009 | 1.09 | 101000 | 0.0085 | 0.9215 |
|
| 152 |
+
| 0.0085 | 1.1 | 102000 | 0.0084 | 0.9216 |
|
| 153 |
+
| 0.0123 | 1.11 | 103000 | 0.0085 | 0.9215 |
|
| 154 |
+
| 0.0094 | 1.12 | 104000 | 0.0084 | 0.9215 |
|
| 155 |
+
| 0.0076 | 1.14 | 105000 | 0.0081 | 0.9215 |
|
| 156 |
+
| 0.0119 | 1.15 | 106000 | 0.0079 | 0.9216 |
|
| 157 |
+
| 0.0079 | 1.16 | 107000 | 0.0081 | 0.9216 |
|
| 158 |
+
| 0.0108 | 1.17 | 108000 | 0.0080 | 0.9216 |
|
| 159 |
+
| 0.01 | 1.18 | 109000 | 0.0077 | 0.9216 |
|
| 160 |
+
| 0.0112 | 1.19 | 110000 | 0.0077 | 0.9216 |
|
| 161 |
+
| 0.0092 | 1.2 | 111000 | 0.0076 | 0.9215 |
|
| 162 |
+
| 0.0097 | 1.21 | 112000 | 0.0077 | 0.9215 |
|
| 163 |
+
| 0.0093 | 1.22 | 113000 | 0.0078 | 0.9215 |
|
| 164 |
+
| 0.0106 | 1.23 | 114000 | 0.0077 | 0.9215 |
|
| 165 |
+
| 0.0107 | 1.24 | 115000 | 0.0076 | 0.9215 |
|
| 166 |
+
| 0.0111 | 1.25 | 116000 | 0.0077 | 0.9215 |
|
| 167 |
+
| 0.0118 | 1.26 | 117000 | 0.0076 | 0.9215 |
|
| 168 |
+
| 0.0088 | 1.28 | 118000 | 0.0076 | 0.9215 |
|
| 169 |
+
| 0.01 | 1.29 | 119000 | 0.0076 | 0.9215 |
|
| 170 |
+
| 0.0102 | 1.3 | 120000 | 0.0076 | 0.9215 |
|
| 171 |
+
| 0.0106 | 1.31 | 121000 | 0.0076 | 0.9215 |
|
| 172 |
+
| 0.0099 | 1.32 | 122000 | 0.0077 | 0.9215 |
|
| 173 |
+
| 0.0099 | 1.33 | 123000 | 0.0077 | 0.9216 |
|
| 174 |
+
| 0.0105 | 1.34 | 124000 | 0.0075 | 0.9216 |
|
| 175 |
+
| 0.0082 | 1.35 | 125000 | 0.0074 | 0.9216 |
|
| 176 |
+
| 0.0088 | 1.36 | 126000 | 0.0072 | 0.9215 |
|
| 177 |
+
| 0.0077 | 1.37 | 127000 | 0.0070 | 0.9215 |
|
| 178 |
+
| 0.0063 | 1.38 | 128000 | 0.0074 | 0.9216 |
|
| 179 |
+
| 0.0084 | 1.39 | 129000 | 0.0069 | 0.9215 |
|
| 180 |
+
| 0.0085 | 1.41 | 130000 | 0.0071 | 0.9215 |
|
| 181 |
+
| 0.0107 | 1.42 | 131000 | 0.0067 | 0.9215 |
|
| 182 |
+
| 0.0064 | 1.43 | 132000 | 0.0068 | 0.9215 |
|
| 183 |
+
| 0.0064 | 1.44 | 133000 | 0.0069 | 0.9215 |
|
| 184 |
+
| 0.0139 | 1.45 | 134000 | 0.0067 | 0.9216 |
|
| 185 |
+
| 0.0093 | 1.46 | 135000 | 0.0068 | 0.9216 |
|
| 186 |
+
| 0.009 | 1.47 | 136000 | 0.0067 | 0.9215 |
|
| 187 |
+
| 0.0083 | 1.48 | 137000 | 0.0065 | 0.9216 |
|
| 188 |
+
| 0.0108 | 1.49 | 138000 | 0.0064 | 0.9215 |
|
| 189 |
+
| 0.0074 | 1.5 | 139000 | 0.0066 | 0.9215 |
|
| 190 |
+
| 0.009 | 1.51 | 140000 | 0.0064 | 0.9216 |
|
| 191 |
+
| 0.0062 | 1.52 | 141000 | 0.0064 | 0.9215 |
|
| 192 |
+
| 0.007 | 1.54 | 142000 | 0.0063 | 0.9215 |
|
| 193 |
+
| 0.0082 | 1.55 | 143000 | 0.0062 | 0.9215 |
|
| 194 |
+
| 0.0077 | 1.56 | 144000 | 0.0064 | 0.9215 |
|
| 195 |
+
| 0.0094 | 1.57 | 145000 | 0.0062 | 0.9215 |
|
| 196 |
+
| 0.0085 | 1.58 | 146000 | 0.0063 | 0.9215 |
|
| 197 |
+
| 0.0091 | 1.59 | 147000 | 0.0062 | 0.9215 |
|
| 198 |
+
| 0.0087 | 1.6 | 148000 | 0.0061 | 0.9215 |
|
| 199 |
+
| 0.0066 | 1.61 | 149000 | 0.0062 | 0.9215 |
|
| 200 |
+
| 0.0087 | 1.62 | 150000 | 0.0061 | 0.9215 |
|
| 201 |
+
| 0.0059 | 1.63 | 151000 | 0.0059 | 0.9215 |
|
| 202 |
+
| 0.0086 | 1.64 | 152000 | 0.0059 | 0.9215 |
|
| 203 |
+
| 0.0066 | 1.65 | 153000 | 0.0059 | 0.9215 |
|
| 204 |
+
| 0.0076 | 1.66 | 154000 | 0.0058 | 0.9215 |
|
| 205 |
+
| 0.0073 | 1.68 | 155000 | 0.0060 | 0.9215 |
|
| 206 |
+
| 0.0118 | 1.69 | 156000 | 0.0060 | 0.9215 |
|
| 207 |
+
| 0.0058 | 1.7 | 157000 | 0.0059 | 0.9215 |
|
| 208 |
+
| 0.0093 | 1.71 | 158000 | 0.0058 | 0.9215 |
|
| 209 |
+
| 0.0079 | 1.72 | 159000 | 0.0058 | 0.9215 |
|
| 210 |
+
| 0.0063 | 1.73 | 160000 | 0.0059 | 0.9215 |
|
| 211 |
+
| 0.0065 | 1.74 | 161000 | 0.0056 | 0.9215 |
|
| 212 |
+
| 0.0105 | 1.75 | 162000 | 0.0057 | 0.9215 |
|
| 213 |
+
| 0.0075 | 1.76 | 163000 | 0.0055 | 0.9215 |
|
| 214 |
+
| 0.0069 | 1.77 | 164000 | 0.0056 | 0.9215 |
|
| 215 |
+
| 0.0075 | 1.78 | 165000 | 0.0056 | 0.9215 |
|
| 216 |
+
| 0.0067 | 1.79 | 166000 | 0.0055 | 0.9215 |
|
| 217 |
+
| 0.0069 | 1.81 | 167000 | 0.0056 | 0.9215 |
|
| 218 |
+
| 0.0063 | 1.82 | 168000 | 0.0056 | 0.9215 |
|
| 219 |
+
| 0.0058 | 1.83 | 169000 | 0.0055 | 0.9215 |
|
| 220 |
+
| 0.0058 | 1.84 | 170000 | 0.0054 | 0.9215 |
|
| 221 |
+
| 0.0081 | 1.85 | 171000 | 0.0055 | 0.9215 |
|
| 222 |
+
| 0.0071 | 1.86 | 172000 | 0.0054 | 0.9215 |
|
| 223 |
+
| 0.0077 | 1.87 | 173000 | 0.0054 | 0.9215 |
|
| 224 |
+
| 0.0053 | 1.88 | 174000 | 0.0053 | 0.9215 |
|
| 225 |
+
| 0.0067 | 1.89 | 175000 | 0.0053 | 0.9215 |
|
| 226 |
+
| 0.0066 | 1.9 | 176000 | 0.0053 | 0.9215 |
|
| 227 |
+
| 0.0084 | 1.91 | 177000 | 0.0053 | 0.9215 |
|
| 228 |
+
| 0.0066 | 1.92 | 178000 | 0.0052 | 0.9215 |
|
| 229 |
+
| 0.0057 | 1.94 | 179000 | 0.0053 | 0.9215 |
|
| 230 |
+
| 0.0059 | 1.95 | 180000 | 0.0052 | 0.9215 |
|
| 231 |
+
| 0.0053 | 1.96 | 181000 | 0.0053 | 0.9215 |
|
| 232 |
+
| 0.0056 | 1.97 | 182000 | 0.0052 | 0.9215 |
|
| 233 |
+
| 0.0054 | 1.98 | 183000 | 0.0052 | 0.9215 |
|
| 234 |
+
| 0.0053 | 1.99 | 184000 | 0.0052 | 0.9215 |
|
| 235 |
+
| 0.0066 | 2.0 | 185000 | 0.0052 | 0.9215 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 236 |
|
| 237 |
|
| 238 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"eval_cer": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 2000,
|
| 7 |
-
"eval_samples_per_second": 1.
|
| 8 |
-
"eval_steps_per_second": 0.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples":
|
| 12 |
-
"train_samples_per_second": 28.
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"eval_cer": 0.01165665167457964,
|
| 4 |
+
"eval_loss": 0.005274078343063593,
|
| 5 |
+
"eval_runtime": 1990.4275,
|
| 6 |
"eval_samples": 2000,
|
| 7 |
+
"eval_samples_per_second": 1.005,
|
| 8 |
+
"eval_steps_per_second": 0.251,
|
| 9 |
+
"train_loss": 0.016045775709704408,
|
| 10 |
+
"train_runtime": 206173.8627,
|
| 11 |
+
"train_samples": 2960086,
|
| 12 |
+
"train_samples_per_second": 28.714,
|
| 13 |
+
"train_steps_per_second": 0.897
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"eval_cer": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 2000,
|
| 7 |
-
"eval_samples_per_second": 1.
|
| 8 |
-
"eval_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"eval_cer": 0.01165665167457964,
|
| 4 |
+
"eval_loss": 0.005274078343063593,
|
| 5 |
+
"eval_runtime": 1990.4275,
|
| 6 |
"eval_samples": 2000,
|
| 7 |
+
"eval_samples_per_second": 1.005,
|
| 8 |
+
"eval_steps_per_second": 0.251
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557971229
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96696783fd7389a128057a8994d2b0151034ffed0645a6a6c5b271c1514f2b0b
|
| 3 |
size 557971229
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 28.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.016045775709704408,
|
| 4 |
+
"train_runtime": 206173.8627,
|
| 5 |
+
"train_samples": 2960086,
|
| 6 |
+
"train_samples_per_second": 28.714,
|
| 7 |
+
"train_steps_per_second": 0.897
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3707
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e466518c4579bd6bee53fdf30377e705184fd9f7e036056a6b09423ab880b7fd
|
| 3 |
size 3707
|