End of training
Browse files- README.md +101 -101
- model.safetensors +1 -1
- runs/Mar10_17-06-23_d0c17e360eb0/events.out.tfevents.1710090384.d0c17e360eb0.144.5 +3 -0
- tokenizer.json +36 -36
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss: 0.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -44,106 +44,106 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
-
| 3.
|
| 48 |
-
| 2.
|
| 49 |
-
| 1.
|
| 50 |
-
| 1.
|
| 51 |
-
| 1.
|
| 52 |
-
| 1.
|
| 53 |
-
| 1.
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
| 0.
|
| 67 |
-
|
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
| 0.
|
| 73 |
-
|
|
| 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 |
|
| 148 |
|
| 149 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.1341
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 44 |
|
| 45 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
+
| 3.4031 | 1.0 | 6 | 2.7477 |
|
| 48 |
+
| 2.3423 | 2.0 | 12 | 2.0656 |
|
| 49 |
+
| 1.7839 | 3.0 | 18 | 1.6402 |
|
| 50 |
+
| 1.6119 | 4.0 | 24 | 1.5371 |
|
| 51 |
+
| 1.544 | 5.0 | 30 | 1.4939 |
|
| 52 |
+
| 1.4631 | 6.0 | 36 | 1.4346 |
|
| 53 |
+
| 1.4052 | 7.0 | 42 | 1.3510 |
|
| 54 |
+
| 1.3137 | 8.0 | 48 | 1.2456 |
|
| 55 |
+
| 1.2297 | 9.0 | 54 | 1.2067 |
|
| 56 |
+
| 1.2454 | 10.0 | 60 | 1.2082 |
|
| 57 |
+
| 1.121 | 11.0 | 66 | 1.0614 |
|
| 58 |
+
| 1.0353 | 12.0 | 72 | 0.9978 |
|
| 59 |
+
| 1.0028 | 13.0 | 78 | 1.0926 |
|
| 60 |
+
| 0.993 | 14.0 | 84 | 0.9551 |
|
| 61 |
+
| 0.9267 | 15.0 | 90 | 0.9013 |
|
| 62 |
+
| 0.8728 | 16.0 | 96 | 0.9764 |
|
| 63 |
+
| 0.9072 | 17.0 | 102 | 0.8508 |
|
| 64 |
+
| 0.8457 | 18.0 | 108 | 0.8541 |
|
| 65 |
+
| 0.8278 | 19.0 | 114 | 0.7950 |
|
| 66 |
+
| 0.7903 | 20.0 | 120 | 0.7892 |
|
| 67 |
+
| 0.7726 | 21.0 | 126 | 0.7708 |
|
| 68 |
+
| 0.7789 | 22.0 | 132 | 0.7830 |
|
| 69 |
+
| 0.7515 | 23.0 | 138 | 0.8062 |
|
| 70 |
+
| 0.7691 | 24.0 | 144 | 0.7276 |
|
| 71 |
+
| 0.7203 | 25.0 | 150 | 0.7205 |
|
| 72 |
+
| 0.7119 | 26.0 | 156 | 0.7131 |
|
| 73 |
+
| 0.6776 | 27.0 | 162 | 0.6892 |
|
| 74 |
+
| 0.6926 | 28.0 | 168 | 0.7582 |
|
| 75 |
+
| 0.7128 | 29.0 | 174 | 0.9174 |
|
| 76 |
+
| 0.8055 | 30.0 | 180 | 0.7222 |
|
| 77 |
+
| 0.7423 | 31.0 | 186 | 0.6740 |
|
| 78 |
+
| 0.6712 | 32.0 | 192 | 0.7917 |
|
| 79 |
+
| 0.6965 | 33.0 | 198 | 0.6726 |
|
| 80 |
+
| 0.652 | 34.0 | 204 | 0.7449 |
|
| 81 |
+
| 0.6963 | 35.0 | 210 | 0.6932 |
|
| 82 |
+
| 0.6652 | 36.0 | 216 | 0.6286 |
|
| 83 |
+
| 0.6164 | 37.0 | 222 | 0.5777 |
|
| 84 |
+
| 0.5848 | 38.0 | 228 | 0.5556 |
|
| 85 |
+
| 0.5657 | 39.0 | 234 | 0.5788 |
|
| 86 |
+
| 0.5631 | 40.0 | 240 | 0.5216 |
|
| 87 |
+
| 0.5315 | 41.0 | 246 | 0.5156 |
|
| 88 |
+
| 0.5277 | 42.0 | 252 | 0.5486 |
|
| 89 |
+
| 0.5498 | 43.0 | 258 | 0.4877 |
|
| 90 |
+
| 0.4836 | 44.0 | 264 | 0.5947 |
|
| 91 |
+
| 0.555 | 45.0 | 270 | 0.4725 |
|
| 92 |
+
| 0.4804 | 46.0 | 276 | 0.4367 |
|
| 93 |
+
| 0.4537 | 47.0 | 282 | 0.4729 |
|
| 94 |
+
| 0.4668 | 48.0 | 288 | 0.3988 |
|
| 95 |
+
| 0.4507 | 49.0 | 294 | 0.4808 |
|
| 96 |
+
| 0.5128 | 50.0 | 300 | 0.4311 |
|
| 97 |
+
| 0.4444 | 51.0 | 306 | 0.4709 |
|
| 98 |
+
| 0.4538 | 52.0 | 312 | 0.3786 |
|
| 99 |
+
| 0.4213 | 53.0 | 318 | 0.3962 |
|
| 100 |
+
| 0.4067 | 54.0 | 324 | 0.3765 |
|
| 101 |
+
| 0.3931 | 55.0 | 330 | 0.4016 |
|
| 102 |
+
| 0.3946 | 56.0 | 336 | 0.3674 |
|
| 103 |
+
| 0.4095 | 57.0 | 342 | 0.3445 |
|
| 104 |
+
| 0.3817 | 58.0 | 348 | 0.3252 |
|
| 105 |
+
| 0.3528 | 59.0 | 354 | 0.3171 |
|
| 106 |
+
| 0.3527 | 60.0 | 360 | 0.3465 |
|
| 107 |
+
| 0.3562 | 61.0 | 366 | 0.3992 |
|
| 108 |
+
| 0.4265 | 62.0 | 372 | 0.3743 |
|
| 109 |
+
| 0.3734 | 63.0 | 378 | 0.3598 |
|
| 110 |
+
| 0.3585 | 64.0 | 384 | 0.3008 |
|
| 111 |
+
| 0.3438 | 65.0 | 390 | 0.2719 |
|
| 112 |
+
| 0.3289 | 66.0 | 396 | 0.2876 |
|
| 113 |
+
| 0.3128 | 67.0 | 402 | 0.2764 |
|
| 114 |
+
| 0.3106 | 68.0 | 408 | 0.2986 |
|
| 115 |
+
| 0.3058 | 69.0 | 414 | 0.2567 |
|
| 116 |
+
| 0.286 | 70.0 | 420 | 0.2762 |
|
| 117 |
+
| 0.2857 | 71.0 | 426 | 0.2732 |
|
| 118 |
+
| 0.2921 | 72.0 | 432 | 0.2728 |
|
| 119 |
+
| 0.3118 | 73.0 | 438 | 0.2352 |
|
| 120 |
+
| 0.2701 | 74.0 | 444 | 0.2204 |
|
| 121 |
+
| 0.2622 | 75.0 | 450 | 0.2114 |
|
| 122 |
+
| 0.2449 | 76.0 | 456 | 0.2262 |
|
| 123 |
+
| 0.2542 | 77.0 | 462 | 0.2446 |
|
| 124 |
+
| 0.259 | 78.0 | 468 | 0.2187 |
|
| 125 |
+
| 0.2852 | 79.0 | 474 | 0.2329 |
|
| 126 |
+
| 0.2587 | 80.0 | 480 | 0.2101 |
|
| 127 |
+
| 0.2491 | 81.0 | 486 | 0.2165 |
|
| 128 |
+
| 0.2291 | 82.0 | 492 | 0.1921 |
|
| 129 |
+
| 0.2286 | 83.0 | 498 | 0.1815 |
|
| 130 |
+
| 0.2095 | 84.0 | 504 | 0.1700 |
|
| 131 |
+
| 0.2256 | 85.0 | 510 | 0.1640 |
|
| 132 |
+
| 0.2088 | 86.0 | 516 | 0.1848 |
|
| 133 |
+
| 0.2087 | 87.0 | 522 | 0.1745 |
|
| 134 |
+
| 0.2025 | 88.0 | 528 | 0.1655 |
|
| 135 |
+
| 0.2003 | 89.0 | 534 | 0.1717 |
|
| 136 |
+
| 0.2007 | 90.0 | 540 | 0.1682 |
|
| 137 |
+
| 0.1862 | 91.0 | 546 | 0.1629 |
|
| 138 |
+
| 0.2005 | 92.0 | 552 | 0.1482 |
|
| 139 |
+
| 0.2003 | 93.0 | 558 | 0.1600 |
|
| 140 |
+
| 0.1876 | 94.0 | 564 | 0.1498 |
|
| 141 |
+
| 0.1929 | 95.0 | 570 | 0.1405 |
|
| 142 |
+
| 0.1772 | 96.0 | 576 | 0.1404 |
|
| 143 |
+
| 0.1797 | 97.0 | 582 | 0.1366 |
|
| 144 |
+
| 0.1734 | 98.0 | 588 | 0.1352 |
|
| 145 |
+
| 0.1686 | 99.0 | 594 | 0.1345 |
|
| 146 |
+
| 0.177 | 100.0 | 600 | 0.1341 |
|
| 147 |
|
| 148 |
|
| 149 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31207604
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:825e9395d880a4571ebc0ba7f1cb60a448c1e1ab2b79eeacd857fafd65a534a6
|
| 3 |
size 31207604
|
runs/Mar10_17-06-23_d0c17e360eb0/events.out.tfevents.1710090384.d0c17e360eb0.144.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c2852fa9ec03194858183dd6ffe4d2d04941566f9e6811c691950b4332a93ae
|
| 3 |
+
size 56960
|
tokenizer.json
CHANGED
|
@@ -113,78 +113,78 @@
|
|
| 113 |
"8": 14,
|
| 114 |
"9": 15,
|
| 115 |
"=": 16,
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
"95": 25,
|
| 125 |
"14": 26,
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
"17": 31,
|
| 131 |
"92": 32,
|
| 132 |
"18": 33,
|
| 133 |
"91": 34,
|
| 134 |
-
"
|
| 135 |
-
"
|
| 136 |
"20": 37,
|
| 137 |
"89": 38,
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
"23": 43,
|
| 143 |
"86": 44,
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
"27": 51,
|
| 151 |
"82": 52
|
| 152 |
},
|
| 153 |
"merges": [
|
| 154 |
-
"9 9",
|
| 155 |
"1 0",
|
| 156 |
-
"9
|
| 157 |
"1 1",
|
| 158 |
-
"9
|
| 159 |
"1 2",
|
| 160 |
-
"9
|
| 161 |
"1 3",
|
|
|
|
| 162 |
"9 5",
|
| 163 |
"1 4",
|
| 164 |
-
"9 4",
|
| 165 |
"1 5",
|
| 166 |
-
"9
|
| 167 |
"1 6",
|
|
|
|
| 168 |
"1 7",
|
| 169 |
"9 2",
|
| 170 |
"1 8",
|
| 171 |
"9 1",
|
| 172 |
-
"9 0",
|
| 173 |
"1 9",
|
|
|
|
| 174 |
"2 0",
|
| 175 |
"8 9",
|
| 176 |
-
"2 1",
|
| 177 |
"8 8",
|
| 178 |
-
"
|
| 179 |
"2 2",
|
|
|
|
| 180 |
"2 3",
|
| 181 |
"8 6",
|
| 182 |
-
"8 5",
|
| 183 |
"2 4",
|
| 184 |
-
"
|
| 185 |
"8 4",
|
| 186 |
-
"
|
| 187 |
"2 6",
|
|
|
|
| 188 |
"2 7",
|
| 189 |
"8 2"
|
| 190 |
]
|
|
|
|
| 113 |
"8": 14,
|
| 114 |
"9": 15,
|
| 115 |
"=": 16,
|
| 116 |
+
"10": 17,
|
| 117 |
+
"99": 18,
|
| 118 |
+
"11": 19,
|
| 119 |
+
"98": 20,
|
| 120 |
+
"12": 21,
|
| 121 |
+
"97": 22,
|
| 122 |
+
"13": 23,
|
| 123 |
+
"96": 24,
|
| 124 |
"95": 25,
|
| 125 |
"14": 26,
|
| 126 |
+
"15": 27,
|
| 127 |
+
"94": 28,
|
| 128 |
+
"16": 29,
|
| 129 |
+
"93": 30,
|
| 130 |
"17": 31,
|
| 131 |
"92": 32,
|
| 132 |
"18": 33,
|
| 133 |
"91": 34,
|
| 134 |
+
"19": 35,
|
| 135 |
+
"90": 36,
|
| 136 |
"20": 37,
|
| 137 |
"89": 38,
|
| 138 |
+
"88": 39,
|
| 139 |
+
"21": 40,
|
| 140 |
+
"22": 41,
|
| 141 |
+
"87": 42,
|
| 142 |
"23": 43,
|
| 143 |
"86": 44,
|
| 144 |
+
"24": 45,
|
| 145 |
+
"85": 46,
|
| 146 |
+
"84": 47,
|
| 147 |
+
"25": 48,
|
| 148 |
+
"26": 49,
|
| 149 |
+
"83": 50,
|
| 150 |
"27": 51,
|
| 151 |
"82": 52
|
| 152 |
},
|
| 153 |
"merges": [
|
|
|
|
| 154 |
"1 0",
|
| 155 |
+
"9 9",
|
| 156 |
"1 1",
|
| 157 |
+
"9 8",
|
| 158 |
"1 2",
|
| 159 |
+
"9 7",
|
| 160 |
"1 3",
|
| 161 |
+
"9 6",
|
| 162 |
"9 5",
|
| 163 |
"1 4",
|
|
|
|
| 164 |
"1 5",
|
| 165 |
+
"9 4",
|
| 166 |
"1 6",
|
| 167 |
+
"9 3",
|
| 168 |
"1 7",
|
| 169 |
"9 2",
|
| 170 |
"1 8",
|
| 171 |
"9 1",
|
|
|
|
| 172 |
"1 9",
|
| 173 |
+
"9 0",
|
| 174 |
"2 0",
|
| 175 |
"8 9",
|
|
|
|
| 176 |
"8 8",
|
| 177 |
+
"2 1",
|
| 178 |
"2 2",
|
| 179 |
+
"8 7",
|
| 180 |
"2 3",
|
| 181 |
"8 6",
|
|
|
|
| 182 |
"2 4",
|
| 183 |
+
"8 5",
|
| 184 |
"8 4",
|
| 185 |
+
"2 5",
|
| 186 |
"2 6",
|
| 187 |
+
"8 3",
|
| 188 |
"2 7",
|
| 189 |
"8 2"
|
| 190 |
]
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaeeadaaaa7bad9629c2f8a8af7342ce79d0c8b9bf98c7b925f3c338218d2fa4
|
| 3 |
size 5112
|