End of training
Browse files- README.md +14 -304
- model.safetensors +1 -1
- runs/Mar29_08-20-42_9688da4f687f/events.out.tfevents.1711700442.9688da4f687f.971.0 +3 -0
- runs/Mar29_08-21-17_9688da4f687f/events.out.tfevents.1711700477.9688da4f687f.971.1 +3 -0
- runs/Mar29_08-21-45_9688da4f687f/events.out.tfevents.1711700505.9688da4f687f.971.2 +3 -0
- runs/Mar29_08-21-45_9688da4f687f/events.out.tfevents.1711700628.9688da4f687f.971.3 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss:
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -35,317 +35,27 @@ More information needed
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0002
|
| 38 |
-
- train_batch_size:
|
| 39 |
-
- eval_batch_size:
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
-
| No log | 1.0 | 1 |
|
| 50 |
-
| No log | 2.0 | 2 |
|
| 51 |
-
| No log | 3.0 | 3 |
|
| 52 |
-
| No log | 4.0 | 4 |
|
| 53 |
-
| No log | 5.0 | 5 |
|
| 54 |
-
| No log | 6.0 | 6 |
|
| 55 |
-
| No log | 7.0 | 7 |
|
| 56 |
-
| No log | 8.0 | 8 |
|
| 57 |
-
| No log | 9.0 | 9 |
|
| 58 |
-
| No log | 10.0 | 10 |
|
| 59 |
-
| No log | 11.0 | 11 | 4.7907 |
|
| 60 |
-
| No log | 12.0 | 12 | 4.8642 |
|
| 61 |
-
| No log | 13.0 | 13 | 4.9226 |
|
| 62 |
-
| No log | 14.0 | 14 | 5.0049 |
|
| 63 |
-
| No log | 15.0 | 15 | 5.1230 |
|
| 64 |
-
| No log | 16.0 | 16 | 5.2132 |
|
| 65 |
-
| No log | 17.0 | 17 | 5.2580 |
|
| 66 |
-
| No log | 18.0 | 18 | 5.2836 |
|
| 67 |
-
| No log | 19.0 | 19 | 5.2780 |
|
| 68 |
-
| No log | 20.0 | 20 | 5.2579 |
|
| 69 |
-
| No log | 21.0 | 21 | 5.2451 |
|
| 70 |
-
| No log | 22.0 | 22 | 5.2365 |
|
| 71 |
-
| No log | 23.0 | 23 | 5.2346 |
|
| 72 |
-
| No log | 24.0 | 24 | 5.2518 |
|
| 73 |
-
| No log | 25.0 | 25 | 5.2774 |
|
| 74 |
-
| No log | 26.0 | 26 | 5.3097 |
|
| 75 |
-
| No log | 27.0 | 27 | 5.3400 |
|
| 76 |
-
| No log | 28.0 | 28 | 5.3913 |
|
| 77 |
-
| No log | 29.0 | 29 | 5.4408 |
|
| 78 |
-
| No log | 30.0 | 30 | 5.4822 |
|
| 79 |
-
| No log | 31.0 | 31 | 5.5076 |
|
| 80 |
-
| No log | 32.0 | 32 | 5.5590 |
|
| 81 |
-
| No log | 33.0 | 33 | 5.6134 |
|
| 82 |
-
| No log | 34.0 | 34 | 5.6600 |
|
| 83 |
-
| No log | 35.0 | 35 | 5.6953 |
|
| 84 |
-
| No log | 36.0 | 36 | 5.7297 |
|
| 85 |
-
| No log | 37.0 | 37 | 5.7620 |
|
| 86 |
-
| No log | 38.0 | 38 | 5.8111 |
|
| 87 |
-
| No log | 39.0 | 39 | 5.8563 |
|
| 88 |
-
| No log | 40.0 | 40 | 5.8710 |
|
| 89 |
-
| No log | 41.0 | 41 | 5.8723 |
|
| 90 |
-
| No log | 42.0 | 42 | 5.8851 |
|
| 91 |
-
| No log | 43.0 | 43 | 5.9023 |
|
| 92 |
-
| No log | 44.0 | 44 | 5.9218 |
|
| 93 |
-
| No log | 45.0 | 45 | 5.9323 |
|
| 94 |
-
| No log | 46.0 | 46 | 5.9256 |
|
| 95 |
-
| No log | 47.0 | 47 | 5.9269 |
|
| 96 |
-
| No log | 48.0 | 48 | 5.9236 |
|
| 97 |
-
| No log | 49.0 | 49 | 5.9186 |
|
| 98 |
-
| No log | 50.0 | 50 | 5.9071 |
|
| 99 |
-
| No log | 51.0 | 51 | 5.8891 |
|
| 100 |
-
| No log | 52.0 | 52 | 5.8800 |
|
| 101 |
-
| No log | 53.0 | 53 | 5.8782 |
|
| 102 |
-
| No log | 54.0 | 54 | 5.8825 |
|
| 103 |
-
| No log | 55.0 | 55 | 5.8933 |
|
| 104 |
-
| No log | 56.0 | 56 | 5.9076 |
|
| 105 |
-
| No log | 57.0 | 57 | 5.9233 |
|
| 106 |
-
| No log | 58.0 | 58 | 5.9443 |
|
| 107 |
-
| No log | 59.0 | 59 | 5.9652 |
|
| 108 |
-
| No log | 60.0 | 60 | 5.9870 |
|
| 109 |
-
| No log | 61.0 | 61 | 6.0095 |
|
| 110 |
-
| No log | 62.0 | 62 | 6.0313 |
|
| 111 |
-
| No log | 63.0 | 63 | 6.0558 |
|
| 112 |
-
| No log | 64.0 | 64 | 6.0709 |
|
| 113 |
-
| No log | 65.0 | 65 | 6.0709 |
|
| 114 |
-
| No log | 66.0 | 66 | 6.0735 |
|
| 115 |
-
| No log | 67.0 | 67 | 6.0716 |
|
| 116 |
-
| No log | 68.0 | 68 | 6.0587 |
|
| 117 |
-
| No log | 69.0 | 69 | 6.0493 |
|
| 118 |
-
| No log | 70.0 | 70 | 6.0352 |
|
| 119 |
-
| No log | 71.0 | 71 | 6.0237 |
|
| 120 |
-
| No log | 72.0 | 72 | 6.0197 |
|
| 121 |
-
| No log | 73.0 | 73 | 6.0148 |
|
| 122 |
-
| No log | 74.0 | 74 | 6.0151 |
|
| 123 |
-
| No log | 75.0 | 75 | 6.0233 |
|
| 124 |
-
| No log | 76.0 | 76 | 6.0378 |
|
| 125 |
-
| No log | 77.0 | 77 | 6.0594 |
|
| 126 |
-
| No log | 78.0 | 78 | 6.0826 |
|
| 127 |
-
| No log | 79.0 | 79 | 6.1049 |
|
| 128 |
-
| No log | 80.0 | 80 | 6.1233 |
|
| 129 |
-
| No log | 81.0 | 81 | 6.1417 |
|
| 130 |
-
| No log | 82.0 | 82 | 6.1617 |
|
| 131 |
-
| No log | 83.0 | 83 | 6.1835 |
|
| 132 |
-
| No log | 84.0 | 84 | 6.1985 |
|
| 133 |
-
| No log | 85.0 | 85 | 6.2137 |
|
| 134 |
-
| No log | 86.0 | 86 | 6.2269 |
|
| 135 |
-
| No log | 87.0 | 87 | 6.2450 |
|
| 136 |
-
| No log | 88.0 | 88 | 6.2646 |
|
| 137 |
-
| No log | 89.0 | 89 | 6.2846 |
|
| 138 |
-
| No log | 90.0 | 90 | 6.2978 |
|
| 139 |
-
| No log | 91.0 | 91 | 6.3107 |
|
| 140 |
-
| No log | 92.0 | 92 | 6.3255 |
|
| 141 |
-
| No log | 93.0 | 93 | 6.3417 |
|
| 142 |
-
| No log | 94.0 | 94 | 6.3559 |
|
| 143 |
-
| No log | 95.0 | 95 | 6.3679 |
|
| 144 |
-
| No log | 96.0 | 96 | 6.3794 |
|
| 145 |
-
| No log | 97.0 | 97 | 6.3561 |
|
| 146 |
-
| No log | 98.0 | 98 | 6.3274 |
|
| 147 |
-
| No log | 99.0 | 99 | 6.3042 |
|
| 148 |
-
| No log | 100.0 | 100 | 6.2891 |
|
| 149 |
-
| No log | 101.0 | 101 | 6.2644 |
|
| 150 |
-
| No log | 102.0 | 102 | 6.2372 |
|
| 151 |
-
| No log | 103.0 | 103 | 6.2225 |
|
| 152 |
-
| No log | 104.0 | 104 | 6.2174 |
|
| 153 |
-
| No log | 105.0 | 105 | 6.2239 |
|
| 154 |
-
| No log | 106.0 | 106 | 6.2080 |
|
| 155 |
-
| No log | 107.0 | 107 | 6.1955 |
|
| 156 |
-
| No log | 108.0 | 108 | 6.1800 |
|
| 157 |
-
| No log | 109.0 | 109 | 6.1664 |
|
| 158 |
-
| No log | 110.0 | 110 | 6.1527 |
|
| 159 |
-
| No log | 111.0 | 111 | 6.1455 |
|
| 160 |
-
| No log | 112.0 | 112 | 6.1408 |
|
| 161 |
-
| No log | 113.0 | 113 | 6.1408 |
|
| 162 |
-
| No log | 114.0 | 114 | 6.1450 |
|
| 163 |
-
| No log | 115.0 | 115 | 6.1543 |
|
| 164 |
-
| No log | 116.0 | 116 | 6.1423 |
|
| 165 |
-
| No log | 117.0 | 117 | 6.1347 |
|
| 166 |
-
| No log | 118.0 | 118 | 6.1202 |
|
| 167 |
-
| No log | 119.0 | 119 | 6.0935 |
|
| 168 |
-
| No log | 120.0 | 120 | 6.0795 |
|
| 169 |
-
| No log | 121.0 | 121 | 6.0698 |
|
| 170 |
-
| No log | 122.0 | 122 | 6.0718 |
|
| 171 |
-
| No log | 123.0 | 123 | 6.0779 |
|
| 172 |
-
| No log | 124.0 | 124 | 6.0872 |
|
| 173 |
-
| No log | 125.0 | 125 | 6.0986 |
|
| 174 |
-
| No log | 126.0 | 126 | 6.1104 |
|
| 175 |
-
| No log | 127.0 | 127 | 6.1281 |
|
| 176 |
-
| No log | 128.0 | 128 | 6.1455 |
|
| 177 |
-
| No log | 129.0 | 129 | 6.1631 |
|
| 178 |
-
| No log | 130.0 | 130 | 6.1812 |
|
| 179 |
-
| No log | 131.0 | 131 | 6.1999 |
|
| 180 |
-
| No log | 132.0 | 132 | 6.2176 |
|
| 181 |
-
| No log | 133.0 | 133 | 6.2295 |
|
| 182 |
-
| No log | 134.0 | 134 | 6.2345 |
|
| 183 |
-
| No log | 135.0 | 135 | 6.2413 |
|
| 184 |
-
| No log | 136.0 | 136 | 6.2493 |
|
| 185 |
-
| No log | 137.0 | 137 | 6.2490 |
|
| 186 |
-
| No log | 138.0 | 138 | 6.2469 |
|
| 187 |
-
| No log | 139.0 | 139 | 6.2482 |
|
| 188 |
-
| No log | 140.0 | 140 | 6.2495 |
|
| 189 |
-
| No log | 141.0 | 141 | 6.2534 |
|
| 190 |
-
| No log | 142.0 | 142 | 6.2593 |
|
| 191 |
-
| No log | 143.0 | 143 | 6.2660 |
|
| 192 |
-
| No log | 144.0 | 144 | 6.2749 |
|
| 193 |
-
| No log | 145.0 | 145 | 6.2797 |
|
| 194 |
-
| No log | 146.0 | 146 | 6.2928 |
|
| 195 |
-
| No log | 147.0 | 147 | 6.3081 |
|
| 196 |
-
| No log | 148.0 | 148 | 6.3190 |
|
| 197 |
-
| No log | 149.0 | 149 | 6.3309 |
|
| 198 |
-
| No log | 150.0 | 150 | 6.3388 |
|
| 199 |
-
| No log | 151.0 | 151 | 6.3372 |
|
| 200 |
-
| No log | 152.0 | 152 | 6.3382 |
|
| 201 |
-
| No log | 153.0 | 153 | 6.3416 |
|
| 202 |
-
| No log | 154.0 | 154 | 6.3459 |
|
| 203 |
-
| No log | 155.0 | 155 | 6.3521 |
|
| 204 |
-
| No log | 156.0 | 156 | 6.3538 |
|
| 205 |
-
| No log | 157.0 | 157 | 6.3584 |
|
| 206 |
-
| No log | 158.0 | 158 | 6.3713 |
|
| 207 |
-
| No log | 159.0 | 159 | 6.3841 |
|
| 208 |
-
| No log | 160.0 | 160 | 6.3957 |
|
| 209 |
-
| No log | 161.0 | 161 | 6.4029 |
|
| 210 |
-
| No log | 162.0 | 162 | 6.4090 |
|
| 211 |
-
| No log | 163.0 | 163 | 6.4138 |
|
| 212 |
-
| No log | 164.0 | 164 | 6.4156 |
|
| 213 |
-
| No log | 165.0 | 165 | 6.4203 |
|
| 214 |
-
| No log | 166.0 | 166 | 6.4225 |
|
| 215 |
-
| No log | 167.0 | 167 | 6.4274 |
|
| 216 |
-
| No log | 168.0 | 168 | 6.4317 |
|
| 217 |
-
| No log | 169.0 | 169 | 6.4359 |
|
| 218 |
-
| No log | 170.0 | 170 | 6.4408 |
|
| 219 |
-
| No log | 171.0 | 171 | 6.4456 |
|
| 220 |
-
| No log | 172.0 | 172 | 6.4513 |
|
| 221 |
-
| No log | 173.0 | 173 | 6.4549 |
|
| 222 |
-
| No log | 174.0 | 174 | 6.4586 |
|
| 223 |
-
| No log | 175.0 | 175 | 6.4622 |
|
| 224 |
-
| No log | 176.0 | 176 | 6.4658 |
|
| 225 |
-
| No log | 177.0 | 177 | 6.4694 |
|
| 226 |
-
| No log | 178.0 | 178 | 6.4732 |
|
| 227 |
-
| No log | 179.0 | 179 | 6.4776 |
|
| 228 |
-
| No log | 180.0 | 180 | 6.4819 |
|
| 229 |
-
| No log | 181.0 | 181 | 6.4865 |
|
| 230 |
-
| No log | 182.0 | 182 | 6.4879 |
|
| 231 |
-
| No log | 183.0 | 183 | 6.4907 |
|
| 232 |
-
| No log | 184.0 | 184 | 6.4935 |
|
| 233 |
-
| No log | 185.0 | 185 | 6.4970 |
|
| 234 |
-
| No log | 186.0 | 186 | 6.5001 |
|
| 235 |
-
| No log | 187.0 | 187 | 6.5038 |
|
| 236 |
-
| No log | 188.0 | 188 | 6.5079 |
|
| 237 |
-
| No log | 189.0 | 189 | 6.5117 |
|
| 238 |
-
| No log | 190.0 | 190 | 6.5157 |
|
| 239 |
-
| No log | 191.0 | 191 | 6.5191 |
|
| 240 |
-
| No log | 192.0 | 192 | 6.5226 |
|
| 241 |
-
| No log | 193.0 | 193 | 6.5260 |
|
| 242 |
-
| No log | 194.0 | 194 | 6.5295 |
|
| 243 |
-
| No log | 195.0 | 195 | 6.5327 |
|
| 244 |
-
| No log | 196.0 | 196 | 6.5293 |
|
| 245 |
-
| No log | 197.0 | 197 | 6.5252 |
|
| 246 |
-
| No log | 198.0 | 198 | 6.5218 |
|
| 247 |
-
| No log | 199.0 | 199 | 6.5191 |
|
| 248 |
-
| No log | 200.0 | 200 | 6.5168 |
|
| 249 |
-
| No log | 201.0 | 201 | 6.5154 |
|
| 250 |
-
| No log | 202.0 | 202 | 6.5144 |
|
| 251 |
-
| No log | 203.0 | 203 | 6.5111 |
|
| 252 |
-
| No log | 204.0 | 204 | 6.5082 |
|
| 253 |
-
| No log | 205.0 | 205 | 6.5059 |
|
| 254 |
-
| No log | 206.0 | 206 | 6.5040 |
|
| 255 |
-
| No log | 207.0 | 207 | 6.5029 |
|
| 256 |
-
| No log | 208.0 | 208 | 6.5024 |
|
| 257 |
-
| No log | 209.0 | 209 | 6.5030 |
|
| 258 |
-
| No log | 210.0 | 210 | 6.5035 |
|
| 259 |
-
| No log | 211.0 | 211 | 6.4887 |
|
| 260 |
-
| No log | 212.0 | 212 | 6.4752 |
|
| 261 |
-
| No log | 213.0 | 213 | 6.4641 |
|
| 262 |
-
| No log | 214.0 | 214 | 6.4550 |
|
| 263 |
-
| No log | 215.0 | 215 | 6.4473 |
|
| 264 |
-
| No log | 216.0 | 216 | 6.4406 |
|
| 265 |
-
| No log | 217.0 | 217 | 6.4351 |
|
| 266 |
-
| No log | 218.0 | 218 | 6.4303 |
|
| 267 |
-
| No log | 219.0 | 219 | 6.4264 |
|
| 268 |
-
| No log | 220.0 | 220 | 6.4213 |
|
| 269 |
-
| No log | 221.0 | 221 | 6.4170 |
|
| 270 |
-
| No log | 222.0 | 222 | 6.4136 |
|
| 271 |
-
| No log | 223.0 | 223 | 6.4067 |
|
| 272 |
-
| No log | 224.0 | 224 | 6.4001 |
|
| 273 |
-
| No log | 225.0 | 225 | 6.3944 |
|
| 274 |
-
| No log | 226.0 | 226 | 6.3902 |
|
| 275 |
-
| No log | 227.0 | 227 | 6.3868 |
|
| 276 |
-
| No log | 228.0 | 228 | 6.3851 |
|
| 277 |
-
| No log | 229.0 | 229 | 6.3843 |
|
| 278 |
-
| No log | 230.0 | 230 | 6.3840 |
|
| 279 |
-
| No log | 231.0 | 231 | 6.3840 |
|
| 280 |
-
| No log | 232.0 | 232 | 6.3843 |
|
| 281 |
-
| No log | 233.0 | 233 | 6.3850 |
|
| 282 |
-
| No log | 234.0 | 234 | 6.3820 |
|
| 283 |
-
| No log | 235.0 | 235 | 6.3797 |
|
| 284 |
-
| No log | 236.0 | 236 | 6.3783 |
|
| 285 |
-
| No log | 237.0 | 237 | 6.3774 |
|
| 286 |
-
| No log | 238.0 | 238 | 6.3769 |
|
| 287 |
-
| No log | 239.0 | 239 | 6.3776 |
|
| 288 |
-
| No log | 240.0 | 240 | 6.3784 |
|
| 289 |
-
| No log | 241.0 | 241 | 6.3791 |
|
| 290 |
-
| No log | 242.0 | 242 | 6.3799 |
|
| 291 |
-
| No log | 243.0 | 243 | 6.3809 |
|
| 292 |
-
| No log | 244.0 | 244 | 6.3823 |
|
| 293 |
-
| No log | 245.0 | 245 | 6.3840 |
|
| 294 |
-
| No log | 246.0 | 246 | 6.3860 |
|
| 295 |
-
| No log | 247.0 | 247 | 6.3879 |
|
| 296 |
-
| No log | 248.0 | 248 | 6.3900 |
|
| 297 |
-
| No log | 249.0 | 249 | 6.3920 |
|
| 298 |
-
| No log | 250.0 | 250 | 6.3940 |
|
| 299 |
-
| No log | 251.0 | 251 | 6.3962 |
|
| 300 |
-
| No log | 252.0 | 252 | 6.3987 |
|
| 301 |
-
| No log | 253.0 | 253 | 6.4011 |
|
| 302 |
-
| No log | 254.0 | 254 | 6.4034 |
|
| 303 |
-
| No log | 255.0 | 255 | 6.4058 |
|
| 304 |
-
| No log | 256.0 | 256 | 6.4086 |
|
| 305 |
-
| No log | 257.0 | 257 | 6.4076 |
|
| 306 |
-
| No log | 258.0 | 258 | 6.4070 |
|
| 307 |
-
| No log | 259.0 | 259 | 6.4074 |
|
| 308 |
-
| No log | 260.0 | 260 | 6.4081 |
|
| 309 |
-
| No log | 261.0 | 261 | 6.4088 |
|
| 310 |
-
| No log | 262.0 | 262 | 6.4095 |
|
| 311 |
-
| No log | 263.0 | 263 | 6.4105 |
|
| 312 |
-
| No log | 264.0 | 264 | 6.4114 |
|
| 313 |
-
| No log | 265.0 | 265 | 6.4123 |
|
| 314 |
-
| No log | 266.0 | 266 | 6.4102 |
|
| 315 |
-
| No log | 267.0 | 267 | 6.4083 |
|
| 316 |
-
| No log | 268.0 | 268 | 6.4068 |
|
| 317 |
-
| No log | 269.0 | 269 | 6.4058 |
|
| 318 |
-
| No log | 270.0 | 270 | 6.4050 |
|
| 319 |
-
| No log | 271.0 | 271 | 6.4044 |
|
| 320 |
-
| No log | 272.0 | 272 | 6.4038 |
|
| 321 |
-
| No log | 273.0 | 273 | 6.4034 |
|
| 322 |
-
| No log | 274.0 | 274 | 6.4032 |
|
| 323 |
-
| No log | 275.0 | 275 | 6.4031 |
|
| 324 |
-
| No log | 276.0 | 276 | 6.4030 |
|
| 325 |
-
| No log | 277.0 | 277 | 6.4032 |
|
| 326 |
-
| No log | 278.0 | 278 | 6.4036 |
|
| 327 |
-
| No log | 279.0 | 279 | 6.4047 |
|
| 328 |
-
| No log | 280.0 | 280 | 6.4061 |
|
| 329 |
-
| No log | 281.0 | 281 | 6.4074 |
|
| 330 |
-
| No log | 282.0 | 282 | 6.4087 |
|
| 331 |
-
| No log | 283.0 | 283 | 6.4099 |
|
| 332 |
-
| No log | 284.0 | 284 | 6.4112 |
|
| 333 |
-
| No log | 285.0 | 285 | 6.4123 |
|
| 334 |
-
| No log | 286.0 | 286 | 6.4133 |
|
| 335 |
-
| No log | 287.0 | 287 | 6.4143 |
|
| 336 |
-
| No log | 288.0 | 288 | 6.4151 |
|
| 337 |
-
| No log | 289.0 | 289 | 6.4158 |
|
| 338 |
-
| No log | 290.0 | 290 | 6.4165 |
|
| 339 |
-
| No log | 291.0 | 291 | 6.4171 |
|
| 340 |
-
| No log | 292.0 | 292 | 6.4175 |
|
| 341 |
-
| No log | 293.0 | 293 | 6.4179 |
|
| 342 |
-
| No log | 294.0 | 294 | 6.4180 |
|
| 343 |
-
| No log | 295.0 | 295 | 6.4180 |
|
| 344 |
-
| No log | 296.0 | 296 | 6.4181 |
|
| 345 |
-
| No log | 297.0 | 297 | 6.4181 |
|
| 346 |
-
| No log | 298.0 | 298 | 6.4182 |
|
| 347 |
-
| No log | 299.0 | 299 | 6.4183 |
|
| 348 |
-
| No log | 300.0 | 300 | 6.4183 |
|
| 349 |
|
| 350 |
|
| 351 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.2938
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0002
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 10
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| No log | 1.0 | 1 | 3.3173 |
|
| 50 |
+
| No log | 2.0 | 2 | 2.6299 |
|
| 51 |
+
| No log | 3.0 | 3 | 2.3821 |
|
| 52 |
+
| No log | 4.0 | 4 | 2.2974 |
|
| 53 |
+
| No log | 5.0 | 5 | 2.2894 |
|
| 54 |
+
| No log | 6.0 | 6 | 2.2968 |
|
| 55 |
+
| No log | 7.0 | 7 | 2.2920 |
|
| 56 |
+
| No log | 8.0 | 8 | 2.2950 |
|
| 57 |
+
| No log | 9.0 | 9 | 2.2973 |
|
| 58 |
+
| No log | 10.0 | 10 | 2.2938 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 327657928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52ee03c0f38cdc0ed14e74c8bd3f9420ea983dd324f4224977d2df09bfc3c338
|
| 3 |
size 327657928
|
runs/Mar29_08-20-42_9688da4f687f/events.out.tfevents.1711700442.9688da4f687f.971.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3d856dc5846fe2d1ad2248f9011216830a2dd56c6f8736dacfc6c8352b87b42
|
| 3 |
+
size 5755
|
runs/Mar29_08-21-17_9688da4f687f/events.out.tfevents.1711700477.9688da4f687f.971.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aba76abb939330b0a87b014bc68f0ee0ad5697aebc753aba82de4ea12520452
|
| 3 |
+
size 5755
|
runs/Mar29_08-21-45_9688da4f687f/events.out.tfevents.1711700505.9688da4f687f.971.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8fae42ccd2c1a0ca651beeb762e7660d8edf0e1dac51ecf276be315a02e0d8f
|
| 3 |
+
size 7884
|
runs/Mar29_08-21-45_9688da4f687f/events.out.tfevents.1711700628.9688da4f687f.971.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:968f6c472e321891f1f9a05e8755fe5b9c213c4d06b310c70d47c1dbf17833a3
|
| 3 |
+
size 354
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c358bc5cc5ea6c851aae330c8f9cea454cdf96df6a85c72894dfaf3f3abacf9
|
| 3 |
size 4856
|