Model save
Browse files- README.md +200 -256
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 4.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -43,265 +43,209 @@ The following hyperparameters were used during training:
|
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
-
| Training Loss | Epoch | Step
|
| 47 |
-
|
| 48 |
-
| No log | 0.0257 | 50
|
| 49 |
-
| No log | 0.0513 | 100
|
| 50 |
-
| No log | 0.0770 | 150
|
| 51 |
-
| No log | 0.1026 | 200
|
| 52 |
-
| No log | 0.1283 | 250
|
| 53 |
-
| No log | 0.1539 | 300
|
| 54 |
-
| No log | 0.1796 | 350
|
| 55 |
-
| No log | 0.2052 | 400
|
| 56 |
-
| No log | 0.2309 | 450
|
| 57 |
-
| 7.
|
| 58 |
-
| 7.
|
| 59 |
-
| 7.
|
| 60 |
-
| 7.
|
| 61 |
-
| 7.
|
| 62 |
-
| 7.
|
| 63 |
-
| 7.
|
| 64 |
-
| 7.
|
| 65 |
-
| 7.
|
| 66 |
-
| 7.
|
| 67 |
-
| 6.
|
| 68 |
-
| 6.
|
| 69 |
-
| 6.
|
| 70 |
-
| 6.
|
| 71 |
-
| 6.
|
| 72 |
-
| 6.
|
| 73 |
-
| 6.
|
| 74 |
-
| 6.
|
| 75 |
-
| 6.
|
| 76 |
-
| 6.
|
| 77 |
-
| 6.
|
| 78 |
-
| 6.
|
| 79 |
-
| 6.
|
| 80 |
-
| 6.
|
| 81 |
-
| 6.
|
| 82 |
-
| 6.
|
| 83 |
-
| 6.
|
| 84 |
-
| 6.
|
| 85 |
-
| 6.
|
| 86 |
-
| 6.
|
| 87 |
-
| 6.
|
| 88 |
-
| 6.
|
| 89 |
-
| 6.
|
| 90 |
-
| 6.
|
| 91 |
-
| 6.
|
| 92 |
-
| 6.
|
| 93 |
-
| 6.
|
| 94 |
-
| 6.
|
| 95 |
-
| 6.
|
| 96 |
-
| 6.
|
| 97 |
-
| 6.
|
| 98 |
-
| 6.
|
| 99 |
-
| 6.
|
| 100 |
-
| 6.
|
| 101 |
-
| 6.
|
| 102 |
-
| 6.
|
| 103 |
-
| 6.
|
| 104 |
-
| 6.
|
| 105 |
-
| 6.
|
| 106 |
-
| 6.
|
| 107 |
-
| 6.
|
| 108 |
-
| 6.
|
| 109 |
-
| 6.
|
| 110 |
-
| 6.
|
| 111 |
-
| 6.
|
| 112 |
-
| 6.
|
| 113 |
-
| 6.
|
| 114 |
-
| 6.
|
| 115 |
-
| 6.
|
| 116 |
-
| 6.
|
| 117 |
-
| 6.
|
| 118 |
-
| 6.
|
| 119 |
-
| 6.
|
| 120 |
-
| 6.
|
| 121 |
-
| 6.
|
| 122 |
-
| 6.
|
| 123 |
-
| 6.
|
| 124 |
-
| 6.
|
| 125 |
-
| 6.
|
| 126 |
-
| 6.
|
| 127 |
-
|
|
| 128 |
-
|
|
| 129 |
-
|
|
| 130 |
-
|
|
| 131 |
-
|
|
| 132 |
-
|
|
| 133 |
-
|
|
| 134 |
-
|
|
| 135 |
-
|
|
| 136 |
-
|
|
| 137 |
-
| 5.
|
| 138 |
-
| 5.
|
| 139 |
-
| 5.
|
| 140 |
-
| 5.
|
| 141 |
-
| 5.
|
| 142 |
-
| 5.
|
| 143 |
-
| 5.
|
| 144 |
-
| 5.
|
| 145 |
-
| 5.
|
| 146 |
-
| 5.
|
| 147 |
-
| 5.
|
| 148 |
-
| 5.
|
| 149 |
-
| 5.
|
| 150 |
-
| 5.
|
| 151 |
-
| 5.
|
| 152 |
-
| 5.
|
| 153 |
-
| 5.
|
| 154 |
-
| 5.
|
| 155 |
-
| 5.
|
| 156 |
-
| 5.
|
| 157 |
-
| 5.
|
| 158 |
-
| 5.
|
| 159 |
-
| 5.
|
| 160 |
-
| 5.
|
| 161 |
-
| 5.
|
| 162 |
-
| 5.
|
| 163 |
-
| 5.
|
| 164 |
-
| 5.
|
| 165 |
-
| 5.
|
| 166 |
-
| 5.
|
| 167 |
-
| 5.
|
| 168 |
-
| 5.
|
| 169 |
-
| 5.
|
| 170 |
-
| 5.
|
| 171 |
-
| 5.
|
| 172 |
-
| 5.
|
| 173 |
-
| 5.
|
| 174 |
-
| 5.
|
| 175 |
-
| 5.
|
| 176 |
-
| 5.
|
| 177 |
-
| 5.
|
| 178 |
-
| 5.
|
| 179 |
-
| 5.
|
| 180 |
-
| 5.
|
| 181 |
-
| 5.
|
| 182 |
-
| 5.
|
| 183 |
-
| 5.
|
| 184 |
-
| 5.
|
| 185 |
-
| 5.
|
| 186 |
-
| 5.
|
| 187 |
-
| 5.
|
| 188 |
-
| 5.
|
| 189 |
-
| 5.
|
| 190 |
-
| 5.
|
| 191 |
-
| 5.
|
| 192 |
-
| 5.
|
| 193 |
-
| 5.
|
| 194 |
-
| 5.
|
| 195 |
-
| 5.
|
| 196 |
-
| 5.
|
| 197 |
-
| 4.
|
| 198 |
-
| 4.
|
| 199 |
-
| 4.
|
| 200 |
-
| 4.
|
| 201 |
-
| 4.
|
| 202 |
-
| 4.
|
| 203 |
-
| 4.
|
| 204 |
-
| 4.
|
| 205 |
-
| 4.
|
| 206 |
-
| 4.
|
| 207 |
-
| 4.
|
| 208 |
-
| 4.
|
| 209 |
-
| 4.
|
| 210 |
-
| 4.
|
| 211 |
-
| 4.
|
| 212 |
-
| 4.
|
| 213 |
-
| 4.
|
| 214 |
-
| 4.
|
| 215 |
-
| 4.
|
| 216 |
-
| 4.
|
| 217 |
-
| 4.
|
| 218 |
-
| 4.
|
| 219 |
-
| 4.
|
| 220 |
-
| 4.
|
| 221 |
-
| 4.
|
| 222 |
-
| 4.
|
| 223 |
-
| 4.
|
| 224 |
-
| 4.
|
| 225 |
-
| 4.
|
| 226 |
-
| 4.
|
| 227 |
-
| 4.
|
| 228 |
-
| 4.
|
| 229 |
-
| 4.
|
| 230 |
-
| 4.
|
| 231 |
-
| 4.
|
| 232 |
-
| 4.
|
| 233 |
-
| 4.
|
| 234 |
-
| 4.
|
| 235 |
-
| 4.
|
| 236 |
-
| 4.
|
| 237 |
-
| 4.
|
| 238 |
-
| 4.
|
| 239 |
-
| 4.
|
| 240 |
-
| 4.
|
| 241 |
-
| 4.
|
| 242 |
-
| 4.
|
| 243 |
-
| 4.
|
| 244 |
-
| 4.5395 | 5.0539 | 9850 | 4.3645 |
|
| 245 |
-
| 4.5395 | 5.0795 | 9900 | 4.3975 |
|
| 246 |
-
| 4.5395 | 5.1052 | 9950 | 4.3407 |
|
| 247 |
-
| 4.4599 | 5.1308 | 10000 | 4.3571 |
|
| 248 |
-
| 4.4599 | 5.1565 | 10050 | 4.3231 |
|
| 249 |
-
| 4.4599 | 5.1821 | 10100 | 4.3576 |
|
| 250 |
-
| 4.4599 | 5.2078 | 10150 | 4.3316 |
|
| 251 |
-
| 4.4599 | 5.2335 | 10200 | 4.3421 |
|
| 252 |
-
| 4.4599 | 5.2591 | 10250 | 4.3236 |
|
| 253 |
-
| 4.4599 | 5.2848 | 10300 | 4.3069 |
|
| 254 |
-
| 4.4599 | 5.3104 | 10350 | 4.3217 |
|
| 255 |
-
| 4.4599 | 5.3361 | 10400 | 4.3043 |
|
| 256 |
-
| 4.4599 | 5.3617 | 10450 | 4.3047 |
|
| 257 |
-
| 4.4038 | 5.3874 | 10500 | 4.2830 |
|
| 258 |
-
| 4.4038 | 5.4130 | 10550 | 4.3164 |
|
| 259 |
-
| 4.4038 | 5.4387 | 10600 | 4.2653 |
|
| 260 |
-
| 4.4038 | 5.4643 | 10650 | 4.2489 |
|
| 261 |
-
| 4.4038 | 5.4900 | 10700 | 4.2620 |
|
| 262 |
-
| 4.4038 | 5.5156 | 10750 | 4.2916 |
|
| 263 |
-
| 4.4038 | 5.5413 | 10800 | 4.2844 |
|
| 264 |
-
| 4.4038 | 5.5670 | 10850 | 4.2230 |
|
| 265 |
-
| 4.4038 | 5.5926 | 10900 | 4.2603 |
|
| 266 |
-
| 4.4038 | 5.6183 | 10950 | 4.2397 |
|
| 267 |
-
| 4.3445 | 5.6439 | 11000 | 4.2355 |
|
| 268 |
-
| 4.3445 | 5.6696 | 11050 | 4.2179 |
|
| 269 |
-
| 4.3445 | 5.6952 | 11100 | 4.2322 |
|
| 270 |
-
| 4.3445 | 5.7209 | 11150 | 4.1959 |
|
| 271 |
-
| 4.3445 | 5.7465 | 11200 | 4.2179 |
|
| 272 |
-
| 4.3445 | 5.7722 | 11250 | 4.2125 |
|
| 273 |
-
| 4.3445 | 5.7978 | 11300 | 4.2359 |
|
| 274 |
-
| 4.3445 | 5.8235 | 11350 | 4.1847 |
|
| 275 |
-
| 4.3445 | 5.8492 | 11400 | 4.2280 |
|
| 276 |
-
| 4.3445 | 5.8748 | 11450 | 4.1967 |
|
| 277 |
-
| 4.2951 | 5.9005 | 11500 | 4.1907 |
|
| 278 |
-
| 4.2951 | 5.9261 | 11550 | 4.1965 |
|
| 279 |
-
| 4.2951 | 5.9518 | 11600 | 4.1721 |
|
| 280 |
-
| 4.2951 | 5.9774 | 11650 | 4.1770 |
|
| 281 |
-
| 4.2951 | 6.0031 | 11700 | 4.1739 |
|
| 282 |
-
| 4.2951 | 6.0287 | 11750 | 4.1292 |
|
| 283 |
-
| 4.2951 | 6.0544 | 11800 | 4.1789 |
|
| 284 |
-
| 4.2951 | 6.0800 | 11850 | 4.1293 |
|
| 285 |
-
| 4.2951 | 6.1057 | 11900 | 4.1327 |
|
| 286 |
-
| 4.2951 | 6.1313 | 11950 | 4.1313 |
|
| 287 |
-
| 4.2224 | 6.1570 | 12000 | 4.1224 |
|
| 288 |
-
| 4.2224 | 6.1827 | 12050 | 4.1306 |
|
| 289 |
-
| 4.2224 | 6.2083 | 12100 | 4.1244 |
|
| 290 |
-
| 4.2224 | 6.2340 | 12150 | 4.1072 |
|
| 291 |
-
| 4.2224 | 6.2596 | 12200 | 4.1029 |
|
| 292 |
-
| 4.2224 | 6.2853 | 12250 | 4.1252 |
|
| 293 |
-
| 4.2224 | 6.3109 | 12300 | 4.0902 |
|
| 294 |
-
| 4.2224 | 6.3366 | 12350 | 4.0728 |
|
| 295 |
-
| 4.2224 | 6.3622 | 12400 | 4.0932 |
|
| 296 |
-
| 4.2224 | 6.3879 | 12450 | 4.0892 |
|
| 297 |
-
| 4.1426 | 6.4135 | 12500 | 4.1014 |
|
| 298 |
-
| 4.1426 | 6.4392 | 12550 | 4.1073 |
|
| 299 |
-
| 4.1426 | 6.4649 | 12600 | 4.0892 |
|
| 300 |
|
| 301 |
|
| 302 |
### Framework versions
|
| 303 |
|
| 304 |
-
- Transformers 4.
|
| 305 |
- Pytorch 2.5.1+cu121
|
| 306 |
- Datasets 3.2.0
|
| 307 |
- Tokenizers 0.21.0
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 4.4196
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 48 |
+
| No log | 0.0257 | 50 | 8.3797 |
|
| 49 |
+
| No log | 0.0513 | 100 | 7.5227 |
|
| 50 |
+
| No log | 0.0770 | 150 | 7.3529 |
|
| 51 |
+
| No log | 0.1026 | 200 | 7.2301 |
|
| 52 |
+
| No log | 0.1283 | 250 | 7.1456 |
|
| 53 |
+
| No log | 0.1539 | 300 | 7.0682 |
|
| 54 |
+
| No log | 0.1796 | 350 | 6.9683 |
|
| 55 |
+
| No log | 0.2052 | 400 | 6.9433 |
|
| 56 |
+
| No log | 0.2309 | 450 | 6.8604 |
|
| 57 |
+
| 7.4105 | 0.2565 | 500 | 6.8596 |
|
| 58 |
+
| 7.4105 | 0.2822 | 550 | 6.8294 |
|
| 59 |
+
| 7.4105 | 0.3079 | 600 | 6.7680 |
|
| 60 |
+
| 7.4105 | 0.3335 | 650 | 6.7519 |
|
| 61 |
+
| 7.4105 | 0.3592 | 700 | 6.7331 |
|
| 62 |
+
| 7.4105 | 0.3848 | 750 | 6.7107 |
|
| 63 |
+
| 7.4105 | 0.4105 | 800 | 6.6847 |
|
| 64 |
+
| 7.4105 | 0.4361 | 850 | 6.6561 |
|
| 65 |
+
| 7.4105 | 0.4618 | 900 | 6.6557 |
|
| 66 |
+
| 7.4105 | 0.4874 | 950 | 6.6287 |
|
| 67 |
+
| 6.7505 | 0.5131 | 1000 | 6.6354 |
|
| 68 |
+
| 6.7505 | 0.5387 | 1050 | 6.5733 |
|
| 69 |
+
| 6.7505 | 0.5644 | 1100 | 6.5636 |
|
| 70 |
+
| 6.7505 | 0.5900 | 1150 | 6.5483 |
|
| 71 |
+
| 6.7505 | 0.6157 | 1200 | 6.5518 |
|
| 72 |
+
| 6.7505 | 0.6414 | 1250 | 6.4987 |
|
| 73 |
+
| 6.7505 | 0.6670 | 1300 | 6.4945 |
|
| 74 |
+
| 6.7505 | 0.6927 | 1350 | 6.4962 |
|
| 75 |
+
| 6.7505 | 0.7183 | 1400 | 6.4961 |
|
| 76 |
+
| 6.7505 | 0.7440 | 1450 | 6.4763 |
|
| 77 |
+
| 6.5509 | 0.7696 | 1500 | 6.4491 |
|
| 78 |
+
| 6.5509 | 0.7953 | 1550 | 6.4612 |
|
| 79 |
+
| 6.5509 | 0.8209 | 1600 | 6.4320 |
|
| 80 |
+
| 6.5509 | 0.8466 | 1650 | 6.4061 |
|
| 81 |
+
| 6.5509 | 0.8722 | 1700 | 6.3827 |
|
| 82 |
+
| 6.5509 | 0.8979 | 1750 | 6.4234 |
|
| 83 |
+
| 6.5509 | 0.9236 | 1800 | 6.4077 |
|
| 84 |
+
| 6.5509 | 0.9492 | 1850 | 6.3888 |
|
| 85 |
+
| 6.5509 | 0.9749 | 1900 | 6.4047 |
|
| 86 |
+
| 6.5509 | 1.0005 | 1950 | 6.3787 |
|
| 87 |
+
| 6.4448 | 1.0262 | 2000 | 6.3541 |
|
| 88 |
+
| 6.4448 | 1.0518 | 2050 | 6.3429 |
|
| 89 |
+
| 6.4448 | 1.0775 | 2100 | 6.3711 |
|
| 90 |
+
| 6.4448 | 1.1031 | 2150 | 6.3378 |
|
| 91 |
+
| 6.4448 | 1.1288 | 2200 | 6.3210 |
|
| 92 |
+
| 6.4448 | 1.1544 | 2250 | 6.3069 |
|
| 93 |
+
| 6.4448 | 1.1801 | 2300 | 6.3027 |
|
| 94 |
+
| 6.4448 | 1.2057 | 2350 | 6.3036 |
|
| 95 |
+
| 6.4448 | 1.2314 | 2400 | 6.2680 |
|
| 96 |
+
| 6.4448 | 1.2571 | 2450 | 6.2663 |
|
| 97 |
+
| 6.3371 | 1.2827 | 2500 | 6.2803 |
|
| 98 |
+
| 6.3371 | 1.3084 | 2550 | 6.2470 |
|
| 99 |
+
| 6.3371 | 1.3340 | 2600 | 6.2468 |
|
| 100 |
+
| 6.3371 | 1.3597 | 2650 | 6.2251 |
|
| 101 |
+
| 6.3371 | 1.3853 | 2700 | 6.2518 |
|
| 102 |
+
| 6.3371 | 1.4110 | 2750 | 6.2393 |
|
| 103 |
+
| 6.3371 | 1.4366 | 2800 | 6.2144 |
|
| 104 |
+
| 6.3371 | 1.4623 | 2850 | 6.1984 |
|
| 105 |
+
| 6.3371 | 1.4879 | 2900 | 6.2156 |
|
| 106 |
+
| 6.3371 | 1.5136 | 2950 | 6.1799 |
|
| 107 |
+
| 6.2807 | 1.5393 | 3000 | 6.1686 |
|
| 108 |
+
| 6.2807 | 1.5649 | 3050 | 6.1705 |
|
| 109 |
+
| 6.2807 | 1.5906 | 3100 | 6.1725 |
|
| 110 |
+
| 6.2807 | 1.6162 | 3150 | 6.1578 |
|
| 111 |
+
| 6.2807 | 1.6419 | 3200 | 6.1476 |
|
| 112 |
+
| 6.2807 | 1.6675 | 3250 | 6.1461 |
|
| 113 |
+
| 6.2807 | 1.6932 | 3300 | 6.1082 |
|
| 114 |
+
| 6.2807 | 1.7188 | 3350 | 6.0867 |
|
| 115 |
+
| 6.2807 | 1.7445 | 3400 | 6.0844 |
|
| 116 |
+
| 6.2807 | 1.7701 | 3450 | 6.0796 |
|
| 117 |
+
| 6.1678 | 1.7958 | 3500 | 6.0698 |
|
| 118 |
+
| 6.1678 | 1.8214 | 3550 | 6.0559 |
|
| 119 |
+
| 6.1678 | 1.8471 | 3600 | 6.0574 |
|
| 120 |
+
| 6.1678 | 1.8728 | 3650 | 5.9871 |
|
| 121 |
+
| 6.1678 | 1.8984 | 3700 | 6.0185 |
|
| 122 |
+
| 6.1678 | 1.9241 | 3750 | 5.9974 |
|
| 123 |
+
| 6.1678 | 1.9497 | 3800 | 5.9540 |
|
| 124 |
+
| 6.1678 | 1.9754 | 3850 | 5.9818 |
|
| 125 |
+
| 6.1678 | 2.0010 | 3900 | 5.9478 |
|
| 126 |
+
| 6.1678 | 2.0267 | 3950 | 5.9191 |
|
| 127 |
+
| 6.0398 | 2.0523 | 4000 | 5.9068 |
|
| 128 |
+
| 6.0398 | 2.0780 | 4050 | 5.9065 |
|
| 129 |
+
| 6.0398 | 2.1036 | 4100 | 5.8807 |
|
| 130 |
+
| 6.0398 | 2.1293 | 4150 | 5.8725 |
|
| 131 |
+
| 6.0398 | 2.1550 | 4200 | 5.8652 |
|
| 132 |
+
| 6.0398 | 2.1806 | 4250 | 5.8551 |
|
| 133 |
+
| 6.0398 | 2.2063 | 4300 | 5.8291 |
|
| 134 |
+
| 6.0398 | 2.2319 | 4350 | 5.7986 |
|
| 135 |
+
| 6.0398 | 2.2576 | 4400 | 5.7718 |
|
| 136 |
+
| 6.0398 | 2.2832 | 4450 | 5.7675 |
|
| 137 |
+
| 5.886 | 2.3089 | 4500 | 5.7314 |
|
| 138 |
+
| 5.886 | 2.3345 | 4550 | 5.7092 |
|
| 139 |
+
| 5.886 | 2.3602 | 4600 | 5.6816 |
|
| 140 |
+
| 5.886 | 2.3858 | 4650 | 5.6676 |
|
| 141 |
+
| 5.886 | 2.4115 | 4700 | 5.6500 |
|
| 142 |
+
| 5.886 | 2.4371 | 4750 | 5.6245 |
|
| 143 |
+
| 5.886 | 2.4628 | 4800 | 5.6070 |
|
| 144 |
+
| 5.886 | 2.4885 | 4850 | 5.5851 |
|
| 145 |
+
| 5.886 | 2.5141 | 4900 | 5.5514 |
|
| 146 |
+
| 5.886 | 2.5398 | 4950 | 5.5332 |
|
| 147 |
+
| 5.6864 | 2.5654 | 5000 | 5.5098 |
|
| 148 |
+
| 5.6864 | 2.5911 | 5050 | 5.4969 |
|
| 149 |
+
| 5.6864 | 2.6167 | 5100 | 5.4332 |
|
| 150 |
+
| 5.6864 | 2.6424 | 5150 | 5.4490 |
|
| 151 |
+
| 5.6864 | 2.6680 | 5200 | 5.4483 |
|
| 152 |
+
| 5.6864 | 2.6937 | 5250 | 5.4290 |
|
| 153 |
+
| 5.6864 | 2.7193 | 5300 | 5.3701 |
|
| 154 |
+
| 5.6864 | 2.7450 | 5350 | 5.3438 |
|
| 155 |
+
| 5.6864 | 2.7707 | 5400 | 5.3415 |
|
| 156 |
+
| 5.6864 | 2.7963 | 5450 | 5.3366 |
|
| 157 |
+
| 5.4976 | 2.8220 | 5500 | 5.2911 |
|
| 158 |
+
| 5.4976 | 2.8476 | 5550 | 5.2683 |
|
| 159 |
+
| 5.4976 | 2.8733 | 5600 | 5.2673 |
|
| 160 |
+
| 5.4976 | 2.8989 | 5650 | 5.2609 |
|
| 161 |
+
| 5.4976 | 2.9246 | 5700 | 5.2166 |
|
| 162 |
+
| 5.4976 | 2.9502 | 5750 | 5.2048 |
|
| 163 |
+
| 5.4976 | 2.9759 | 5800 | 5.2229 |
|
| 164 |
+
| 5.4976 | 3.0015 | 5850 | 5.1755 |
|
| 165 |
+
| 5.4976 | 3.0272 | 5900 | 5.1560 |
|
| 166 |
+
| 5.4976 | 3.0528 | 5950 | 5.1630 |
|
| 167 |
+
| 5.3186 | 3.0785 | 6000 | 5.1213 |
|
| 168 |
+
| 5.3186 | 3.1042 | 6050 | 5.1381 |
|
| 169 |
+
| 5.3186 | 3.1298 | 6100 | 5.1029 |
|
| 170 |
+
| 5.3186 | 3.1555 | 6150 | 5.1000 |
|
| 171 |
+
| 5.3186 | 3.1811 | 6200 | 5.0759 |
|
| 172 |
+
| 5.3186 | 3.2068 | 6250 | 5.1004 |
|
| 173 |
+
| 5.3186 | 3.2324 | 6300 | 5.0859 |
|
| 174 |
+
| 5.3186 | 3.2581 | 6350 | 5.0483 |
|
| 175 |
+
| 5.3186 | 3.2837 | 6400 | 5.0596 |
|
| 176 |
+
| 5.3186 | 3.3094 | 6450 | 5.0107 |
|
| 177 |
+
| 5.1601 | 3.3350 | 6500 | 5.0064 |
|
| 178 |
+
| 5.1601 | 3.3607 | 6550 | 5.0099 |
|
| 179 |
+
| 5.1601 | 3.3864 | 6600 | 4.9871 |
|
| 180 |
+
| 5.1601 | 3.4120 | 6650 | 4.9469 |
|
| 181 |
+
| 5.1601 | 3.4377 | 6700 | 4.9580 |
|
| 182 |
+
| 5.1601 | 3.4633 | 6750 | 4.9488 |
|
| 183 |
+
| 5.1601 | 3.4890 | 6800 | 4.9288 |
|
| 184 |
+
| 5.1601 | 3.5146 | 6850 | 4.9337 |
|
| 185 |
+
| 5.1601 | 3.5403 | 6900 | 4.9247 |
|
| 186 |
+
| 5.1601 | 3.5659 | 6950 | 4.8895 |
|
| 187 |
+
| 5.0217 | 3.5916 | 7000 | 4.8785 |
|
| 188 |
+
| 5.0217 | 3.6172 | 7050 | 4.8601 |
|
| 189 |
+
| 5.0217 | 3.6429 | 7100 | 4.8779 |
|
| 190 |
+
| 5.0217 | 3.6685 | 7150 | 4.8486 |
|
| 191 |
+
| 5.0217 | 3.6942 | 7200 | 4.8419 |
|
| 192 |
+
| 5.0217 | 3.7199 | 7250 | 4.8239 |
|
| 193 |
+
| 5.0217 | 3.7455 | 7300 | 4.8050 |
|
| 194 |
+
| 5.0217 | 3.7712 | 7350 | 4.8172 |
|
| 195 |
+
| 5.0217 | 3.7968 | 7400 | 4.7992 |
|
| 196 |
+
| 5.0217 | 3.8225 | 7450 | 4.7808 |
|
| 197 |
+
| 4.9197 | 3.8481 | 7500 | 4.7881 |
|
| 198 |
+
| 4.9197 | 3.8738 | 7550 | 4.7625 |
|
| 199 |
+
| 4.9197 | 3.8994 | 7600 | 4.7535 |
|
| 200 |
+
| 4.9197 | 3.9251 | 7650 | 4.7548 |
|
| 201 |
+
| 4.9197 | 3.9507 | 7700 | 4.7273 |
|
| 202 |
+
| 4.9197 | 3.9764 | 7750 | 4.7182 |
|
| 203 |
+
| 4.9197 | 4.0021 | 7800 | 4.7155 |
|
| 204 |
+
| 4.9197 | 4.0277 | 7850 | 4.7128 |
|
| 205 |
+
| 4.9197 | 4.0534 | 7900 | 4.6831 |
|
| 206 |
+
| 4.9197 | 4.0790 | 7950 | 4.6892 |
|
| 207 |
+
| 4.7891 | 4.1047 | 8000 | 4.6848 |
|
| 208 |
+
| 4.7891 | 4.1303 | 8050 | 4.6873 |
|
| 209 |
+
| 4.7891 | 4.1560 | 8100 | 4.6718 |
|
| 210 |
+
| 4.7891 | 4.1816 | 8150 | 4.6474 |
|
| 211 |
+
| 4.7891 | 4.2073 | 8200 | 4.6205 |
|
| 212 |
+
| 4.7891 | 4.2329 | 8250 | 4.6165 |
|
| 213 |
+
| 4.7891 | 4.2586 | 8300 | 4.6393 |
|
| 214 |
+
| 4.7891 | 4.2842 | 8350 | 4.6185 |
|
| 215 |
+
| 4.7891 | 4.3099 | 8400 | 4.6013 |
|
| 216 |
+
| 4.7891 | 4.3356 | 8450 | 4.5950 |
|
| 217 |
+
| 4.6944 | 4.3612 | 8500 | 4.5838 |
|
| 218 |
+
| 4.6944 | 4.3869 | 8550 | 4.5706 |
|
| 219 |
+
| 4.6944 | 4.4125 | 8600 | 4.5776 |
|
| 220 |
+
| 4.6944 | 4.4382 | 8650 | 4.5625 |
|
| 221 |
+
| 4.6944 | 4.4638 | 8700 | 4.5703 |
|
| 222 |
+
| 4.6944 | 4.4895 | 8750 | 4.5489 |
|
| 223 |
+
| 4.6944 | 4.5151 | 8800 | 4.5522 |
|
| 224 |
+
| 4.6944 | 4.5408 | 8850 | 4.5127 |
|
| 225 |
+
| 4.6944 | 4.5664 | 8900 | 4.5183 |
|
| 226 |
+
| 4.6944 | 4.5921 | 8950 | 4.5268 |
|
| 227 |
+
| 4.6262 | 4.6178 | 9000 | 4.4896 |
|
| 228 |
+
| 4.6262 | 4.6434 | 9050 | 4.5180 |
|
| 229 |
+
| 4.6262 | 4.6691 | 9100 | 4.4874 |
|
| 230 |
+
| 4.6262 | 4.6947 | 9150 | 4.4849 |
|
| 231 |
+
| 4.6262 | 4.7204 | 9200 | 4.5018 |
|
| 232 |
+
| 4.6262 | 4.7460 | 9250 | 4.4922 |
|
| 233 |
+
| 4.6262 | 4.7717 | 9300 | 4.4627 |
|
| 234 |
+
| 4.6262 | 4.7973 | 9350 | 4.4675 |
|
| 235 |
+
| 4.6262 | 4.8230 | 9400 | 4.4472 |
|
| 236 |
+
| 4.6262 | 4.8486 | 9450 | 4.4290 |
|
| 237 |
+
| 4.5552 | 4.8743 | 9500 | 4.4188 |
|
| 238 |
+
| 4.5552 | 4.8999 | 9550 | 4.3959 |
|
| 239 |
+
| 4.5552 | 4.9256 | 9600 | 4.4228 |
|
| 240 |
+
| 4.5552 | 4.9513 | 9650 | 4.4267 |
|
| 241 |
+
| 4.5552 | 4.9769 | 9700 | 4.4063 |
|
| 242 |
+
| 4.5552 | 5.0026 | 9750 | 4.4001 |
|
| 243 |
+
| 4.5552 | 5.0282 | 9800 | 4.4196 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 244 |
|
| 245 |
|
| 246 |
### Framework versions
|
| 247 |
|
| 248 |
+
- Transformers 4.48.3
|
| 249 |
- Pytorch 2.5.1+cu121
|
| 250 |
- Datasets 3.2.0
|
| 251 |
- Tokenizers 0.21.0
|
config.json
CHANGED
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"pad_token_id": 0,
|
| 18 |
"position_embedding_type": "absolute",
|
| 19 |
"torch_dtype": "float32",
|
| 20 |
-
"transformers_version": "4.
|
| 21 |
"type_vocab_size": 2,
|
| 22 |
"use_cache": true,
|
| 23 |
"vocab_size": 50000
|
|
|
|
| 17 |
"pad_token_id": 0,
|
| 18 |
"position_embedding_type": "absolute",
|
| 19 |
"torch_dtype": "float32",
|
| 20 |
+
"transformers_version": "4.48.3",
|
| 21 |
"type_vocab_size": 2,
|
| 22 |
"use_cache": true,
|
| 23 |
"vocab_size": 50000
|
generation_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"pad_token_id": 0,
|
| 4 |
-
"transformers_version": "4.
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.48.3"
|
| 5 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 327874976
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b89ce7bc021c7ffc064ea0f32999afd9a4d66940b47f21ff06dcd54a845539e
|
| 3 |
size 327874976
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dc32e7055f652595579fc2a138c6e480d6dcd14037e76b0f865e3103dc75b75
|
| 3 |
size 5304
|