End of training
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -56,7 +56,6 @@ The following hyperparameters were used during training:
|
|
| 56 |
- train_batch_size: 32
|
| 57 |
- eval_batch_size: 64
|
| 58 |
- seed: 42
|
| 59 |
-
- distributed_type: multi-GPU
|
| 60 |
- gradient_accumulation_steps: 2
|
| 61 |
- total_train_batch_size: 64
|
| 62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
@@ -68,73 +67,127 @@ The following hyperparameters were used during training:
|
|
| 68 |
|
| 69 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 70 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 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 |
|
| 134 |
|
| 135 |
### Framework versions
|
| 136 |
|
| 137 |
-
- Transformers 4.
|
| 138 |
- Pytorch 2.0.1+cu118
|
| 139 |
- Datasets 2.14.5
|
| 140 |
-
- Tokenizers 0.
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9231651376146789
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2156
|
| 36 |
+
- Accuracy: 0.9232
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 56 |
- train_batch_size: 32
|
| 57 |
- eval_batch_size: 64
|
| 58 |
- seed: 42
|
|
|
|
| 59 |
- gradient_accumulation_steps: 2
|
| 60 |
- total_train_batch_size: 64
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 0.6905 | 0.01 | 10 | 0.7366 | 0.5080 |
|
| 71 |
+
| 0.684 | 0.02 | 20 | 0.7306 | 0.5069 |
|
| 72 |
+
| 0.7013 | 0.03 | 30 | 0.7228 | 0.5080 |
|
| 73 |
+
| 0.6954 | 0.04 | 40 | 0.7114 | 0.5046 |
|
| 74 |
+
| 0.6893 | 0.05 | 50 | 0.7026 | 0.5034 |
|
| 75 |
+
| 0.6888 | 0.06 | 60 | 0.6912 | 0.5023 |
|
| 76 |
+
| 0.6814 | 0.07 | 70 | 0.6848 | 0.5034 |
|
| 77 |
+
| 0.679 | 0.08 | 80 | 0.6745 | 0.5206 |
|
| 78 |
+
| 0.6616 | 0.09 | 90 | 0.6685 | 0.5252 |
|
| 79 |
+
| 0.6604 | 0.1 | 100 | 0.6580 | 0.5378 |
|
| 80 |
+
| 0.6524 | 0.1 | 110 | 0.6378 | 0.6525 |
|
| 81 |
+
| 0.6344 | 0.11 | 120 | 0.6128 | 0.7271 |
|
| 82 |
+
| 0.5915 | 0.12 | 130 | 0.5672 | 0.8016 |
|
| 83 |
+
| 0.562 | 0.13 | 140 | 0.4903 | 0.8578 |
|
| 84 |
+
| 0.4653 | 0.14 | 150 | 0.3825 | 0.8796 |
|
| 85 |
+
| 0.3632 | 0.15 | 160 | 0.2811 | 0.8991 |
|
| 86 |
+
| 0.2754 | 0.16 | 170 | 0.3029 | 0.8933 |
|
| 87 |
+
| 0.2298 | 0.17 | 180 | 0.3001 | 0.8991 |
|
| 88 |
+
| 0.2819 | 0.18 | 190 | 0.2636 | 0.9083 |
|
| 89 |
+
| 0.2532 | 0.19 | 200 | 0.2321 | 0.9128 |
|
| 90 |
+
| 0.2512 | 0.2 | 210 | 0.2286 | 0.9186 |
|
| 91 |
+
| 0.2149 | 0.21 | 220 | 0.2424 | 0.9128 |
|
| 92 |
+
| 0.2466 | 0.22 | 230 | 0.2505 | 0.9140 |
|
| 93 |
+
| 0.1853 | 0.23 | 240 | 0.2178 | 0.9186 |
|
| 94 |
+
| 0.2279 | 0.24 | 250 | 0.2152 | 0.9186 |
|
| 95 |
+
| 0.219 | 0.25 | 260 | 0.2188 | 0.9197 |
|
| 96 |
+
| 0.2144 | 0.26 | 270 | 0.2179 | 0.9209 |
|
| 97 |
+
| 0.1507 | 0.27 | 280 | 0.2185 | 0.9186 |
|
| 98 |
+
| 0.1801 | 0.28 | 290 | 0.2473 | 0.9243 |
|
| 99 |
+
| 0.1735 | 0.29 | 300 | 0.2402 | 0.9128 |
|
| 100 |
+
| 0.1437 | 0.29 | 310 | 0.2436 | 0.9255 |
|
| 101 |
+
| 0.2221 | 0.3 | 320 | 0.2209 | 0.9163 |
|
| 102 |
+
| 0.1611 | 0.31 | 330 | 0.2101 | 0.9232 |
|
| 103 |
+
| 0.1813 | 0.32 | 340 | 0.2291 | 0.9174 |
|
| 104 |
+
| 0.1871 | 0.33 | 350 | 0.2386 | 0.9174 |
|
| 105 |
+
| 0.2126 | 0.34 | 360 | 0.2225 | 0.9197 |
|
| 106 |
+
| 0.2023 | 0.35 | 370 | 0.2116 | 0.9232 |
|
| 107 |
+
| 0.127 | 0.36 | 380 | 0.2155 | 0.9232 |
|
| 108 |
+
| 0.2769 | 0.37 | 390 | 0.2149 | 0.9243 |
|
| 109 |
+
| 0.1457 | 0.38 | 400 | 0.2166 | 0.9232 |
|
| 110 |
+
| 0.2129 | 0.39 | 410 | 0.2271 | 0.9232 |
|
| 111 |
+
| 0.1652 | 0.4 | 420 | 0.2308 | 0.9220 |
|
| 112 |
+
| 0.1783 | 0.41 | 430 | 0.2400 | 0.9278 |
|
| 113 |
+
| 0.1305 | 0.42 | 440 | 0.2404 | 0.9232 |
|
| 114 |
+
| 0.2595 | 0.43 | 450 | 0.2389 | 0.9209 |
|
| 115 |
+
| 0.1901 | 0.44 | 460 | 0.2102 | 0.9266 |
|
| 116 |
+
| 0.1993 | 0.45 | 470 | 0.2129 | 0.9255 |
|
| 117 |
+
| 0.147 | 0.46 | 480 | 0.2208 | 0.9232 |
|
| 118 |
+
| 0.1801 | 0.47 | 490 | 0.2143 | 0.9255 |
|
| 119 |
+
| 0.1716 | 0.48 | 500 | 0.2416 | 0.9209 |
|
| 120 |
+
| 0.1281 | 0.48 | 510 | 0.2152 | 0.9232 |
|
| 121 |
+
| 0.1837 | 0.49 | 520 | 0.2112 | 0.9243 |
|
| 122 |
+
| 0.1681 | 0.5 | 530 | 0.2178 | 0.9232 |
|
| 123 |
+
| 0.1408 | 0.51 | 540 | 0.2127 | 0.9243 |
|
| 124 |
+
| 0.1229 | 0.52 | 550 | 0.3322 | 0.9278 |
|
| 125 |
+
| 0.1304 | 0.53 | 560 | 0.3586 | 0.9209 |
|
| 126 |
+
| 0.1905 | 0.54 | 570 | 0.3354 | 0.9243 |
|
| 127 |
+
| 0.147 | 0.55 | 580 | 0.3431 | 0.9278 |
|
| 128 |
+
| 0.1538 | 0.56 | 590 | 0.3444 | 0.9232 |
|
| 129 |
+
| 0.1504 | 0.57 | 600 | 0.2196 | 0.9266 |
|
| 130 |
+
| 0.1628 | 0.58 | 610 | 0.3452 | 0.9163 |
|
| 131 |
+
| 0.1387 | 0.59 | 620 | 0.3282 | 0.9278 |
|
| 132 |
+
| 0.2104 | 0.6 | 630 | 0.2132 | 0.9243 |
|
| 133 |
+
| 0.1482 | 0.61 | 640 | 0.2154 | 0.9243 |
|
| 134 |
+
| 0.217 | 0.62 | 650 | 0.3472 | 0.9197 |
|
| 135 |
+
| 0.1692 | 0.63 | 660 | 0.2063 | 0.9243 |
|
| 136 |
+
| 0.175 | 0.64 | 670 | 0.2019 | 0.9278 |
|
| 137 |
+
| 0.1473 | 0.65 | 680 | 0.1957 | 0.9266 |
|
| 138 |
+
| 0.1154 | 0.66 | 690 | 0.2020 | 0.9255 |
|
| 139 |
+
| 0.1369 | 0.67 | 700 | 0.2087 | 0.9266 |
|
| 140 |
+
| 0.1262 | 0.67 | 710 | 0.3224 | 0.9289 |
|
| 141 |
+
| 0.2111 | 0.68 | 720 | 0.3325 | 0.9243 |
|
| 142 |
+
| 0.1349 | 0.69 | 730 | 0.3285 | 0.9289 |
|
| 143 |
+
| 0.1814 | 0.7 | 740 | 0.3324 | 0.9266 |
|
| 144 |
+
| 0.1217 | 0.71 | 750 | 0.3212 | 0.9243 |
|
| 145 |
+
| 0.173 | 0.72 | 760 | 0.2176 | 0.9220 |
|
| 146 |
+
| 0.1441 | 0.73 | 770 | 0.2130 | 0.9232 |
|
| 147 |
+
| 0.1706 | 0.74 | 780 | 0.2136 | 0.9220 |
|
| 148 |
+
| 0.1411 | 0.75 | 790 | 0.2101 | 0.9220 |
|
| 149 |
+
| 0.1051 | 0.76 | 800 | 0.2078 | 0.9243 |
|
| 150 |
+
| 0.115 | 0.77 | 810 | 0.2160 | 0.9266 |
|
| 151 |
+
| 0.2031 | 0.78 | 820 | 0.2162 | 0.9209 |
|
| 152 |
+
| 0.12 | 0.79 | 830 | 0.2059 | 0.9255 |
|
| 153 |
+
| 0.176 | 0.8 | 840 | 0.2100 | 0.9255 |
|
| 154 |
+
| 0.1306 | 0.81 | 850 | 0.4307 | 0.9243 |
|
| 155 |
+
| 0.1359 | 0.82 | 860 | 0.4397 | 0.9289 |
|
| 156 |
+
| 0.1921 | 0.83 | 870 | 0.5446 | 0.9278 |
|
| 157 |
+
| 0.1772 | 0.84 | 880 | 0.5423 | 0.9266 |
|
| 158 |
+
| 0.1771 | 0.85 | 890 | 0.4273 | 0.9266 |
|
| 159 |
+
| 0.1965 | 0.86 | 900 | 0.3224 | 0.9243 |
|
| 160 |
+
| 0.1227 | 0.86 | 910 | 0.2131 | 0.9278 |
|
| 161 |
+
| 0.2046 | 0.87 | 920 | 0.3130 | 0.9278 |
|
| 162 |
+
| 0.1061 | 0.88 | 930 | 0.3180 | 0.9289 |
|
| 163 |
+
| 0.1364 | 0.89 | 940 | 0.5501 | 0.9186 |
|
| 164 |
+
| 0.1213 | 0.9 | 950 | 0.4400 | 0.9220 |
|
| 165 |
+
| 0.1611 | 0.91 | 960 | 0.4364 | 0.9255 |
|
| 166 |
+
| 0.1632 | 0.92 | 970 | 0.4475 | 0.9220 |
|
| 167 |
+
| 0.1617 | 0.93 | 980 | 0.5758 | 0.9209 |
|
| 168 |
+
| 0.1478 | 0.94 | 990 | 0.2143 | 0.9220 |
|
| 169 |
+
| 0.1314 | 0.95 | 1000 | 0.2156 | 0.9232 |
|
| 170 |
+
| 0.1814 | 0.96 | 1010 | 0.2191 | 0.9220 |
|
| 171 |
+
| 0.1669 | 0.97 | 1020 | 0.2129 | 0.9243 |
|
| 172 |
+
| 0.1206 | 0.98 | 1030 | 0.2119 | 0.9220 |
|
| 173 |
+
| 0.1852 | 0.99 | 1040 | 0.2104 | 0.9209 |
|
| 174 |
+
| 0.1381 | 1.0 | 1050 | 0.1999 | 0.9255 |
|
| 175 |
+
| 0.135 | 1.01 | 1060 | 0.2090 | 0.9243 |
|
| 176 |
+
| 0.1253 | 1.02 | 1070 | 0.4486 | 0.9209 |
|
| 177 |
+
| 0.1244 | 1.03 | 1080 | 0.4319 | 0.9197 |
|
| 178 |
+
| 0.1772 | 1.04 | 1090 | 0.4248 | 0.9243 |
|
| 179 |
+
| 0.1264 | 1.05 | 1100 | 0.3090 | 0.9289 |
|
| 180 |
+
| 0.6928 | 1.05 | 1110 | 0.3174 | 0.9278 |
|
| 181 |
+
| 0.0908 | 1.06 | 1120 | 0.4359 | 0.9266 |
|
| 182 |
+
| 0.1286 | 1.07 | 1130 | 0.4302 | 0.9312 |
|
| 183 |
+
| 0.0953 | 1.08 | 1140 | 0.5397 | 0.9289 |
|
| 184 |
+
| 0.1091 | 1.09 | 1150 | 0.5455 | 0.9255 |
|
| 185 |
+
| 0.1546 | 1.1 | 1160 | 0.4261 | 0.9300 |
|
| 186 |
|
| 187 |
|
| 188 |
### Framework versions
|
| 189 |
|
| 190 |
+
- Transformers 4.34.0
|
| 191 |
- Pytorch 2.0.1+cu118
|
| 192 |
- Datasets 2.14.5
|
| 193 |
+
- Tokenizers 0.14.1
|