update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imdb
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: IMDB_DistilBERT_5E
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: imdb
|
| 17 |
+
type: imdb
|
| 18 |
+
config: plain_text
|
| 19 |
+
split: train
|
| 20 |
+
args: plain_text
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.9333333333333333
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# IMDB_DistilBERT_5E
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2309
|
| 35 |
+
- Accuracy: 0.9333
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 1e-05
|
| 55 |
+
- train_batch_size: 16
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 5
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 65 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 66 |
+
| 0.6706 | 0.03 | 50 | 0.5746 | 0.8533 |
|
| 67 |
+
| 0.4323 | 0.06 | 100 | 0.2900 | 0.9 |
|
| 68 |
+
| 0.314 | 0.1 | 150 | 0.2334 | 0.9067 |
|
| 69 |
+
| 0.3062 | 0.13 | 200 | 0.1884 | 0.94 |
|
| 70 |
+
| 0.2834 | 0.16 | 250 | 0.1880 | 0.9267 |
|
| 71 |
+
| 0.2751 | 0.19 | 300 | 0.1944 | 0.94 |
|
| 72 |
+
| 0.2258 | 0.22 | 350 | 0.2003 | 0.9267 |
|
| 73 |
+
| 0.2631 | 0.26 | 400 | 0.1507 | 0.9467 |
|
| 74 |
+
| 0.2661 | 0.29 | 450 | 0.1536 | 0.9467 |
|
| 75 |
+
| 0.2481 | 0.32 | 500 | 0.1533 | 0.94 |
|
| 76 |
+
| 0.2746 | 0.35 | 550 | 0.1402 | 0.9533 |
|
| 77 |
+
| 0.2539 | 0.38 | 600 | 0.1331 | 0.94 |
|
| 78 |
+
| 0.2673 | 0.42 | 650 | 0.1404 | 0.9467 |
|
| 79 |
+
| 0.2438 | 0.45 | 700 | 0.1213 | 0.96 |
|
| 80 |
+
| 0.2355 | 0.48 | 750 | 0.1181 | 0.9533 |
|
| 81 |
+
| 0.2059 | 0.51 | 800 | 0.1417 | 0.9333 |
|
| 82 |
+
| 0.2585 | 0.54 | 850 | 0.1257 | 0.9533 |
|
| 83 |
+
| 0.2331 | 0.58 | 900 | 0.1307 | 0.94 |
|
| 84 |
+
| 0.2602 | 0.61 | 950 | 0.1172 | 0.9467 |
|
| 85 |
+
| 0.24 | 0.64 | 1000 | 0.1141 | 0.9533 |
|
| 86 |
+
| 0.2169 | 0.67 | 1050 | 0.1198 | 0.94 |
|
| 87 |
+
| 0.2796 | 0.7 | 1100 | 0.1171 | 0.9533 |
|
| 88 |
+
| 0.2559 | 0.74 | 1150 | 0.1199 | 0.96 |
|
| 89 |
+
| 0.2377 | 0.77 | 1200 | 0.1359 | 0.9333 |
|
| 90 |
+
| 0.2268 | 0.8 | 1250 | 0.1235 | 0.9533 |
|
| 91 |
+
| 0.2422 | 0.83 | 1300 | 0.1439 | 0.9333 |
|
| 92 |
+
| 0.2101 | 0.86 | 1350 | 0.1333 | 0.9333 |
|
| 93 |
+
| 0.1875 | 0.9 | 1400 | 0.1206 | 0.9467 |
|
| 94 |
+
| 0.2279 | 0.93 | 1450 | 0.1136 | 0.96 |
|
| 95 |
+
| 0.2214 | 0.96 | 1500 | 0.1188 | 0.9467 |
|
| 96 |
+
| 0.2416 | 0.99 | 1550 | 0.1029 | 0.9467 |
|
| 97 |
+
| 0.219 | 1.02 | 1600 | 0.1113 | 0.94 |
|
| 98 |
+
| 0.1806 | 1.06 | 1650 | 0.1095 | 0.9533 |
|
| 99 |
+
| 0.1343 | 1.09 | 1700 | 0.1630 | 0.94 |
|
| 100 |
+
| 0.1699 | 1.12 | 1750 | 0.1221 | 0.96 |
|
| 101 |
+
| 0.1837 | 1.15 | 1800 | 0.1213 | 0.9467 |
|
| 102 |
+
| 0.1763 | 1.18 | 1850 | 0.1286 | 0.9533 |
|
| 103 |
+
| 0.1856 | 1.22 | 1900 | 0.1531 | 0.9267 |
|
| 104 |
+
| 0.1647 | 1.25 | 1950 | 0.1380 | 0.9533 |
|
| 105 |
+
| 0.2204 | 1.28 | 2000 | 0.1268 | 0.9333 |
|
| 106 |
+
| 0.1774 | 1.31 | 2050 | 0.1689 | 0.9267 |
|
| 107 |
+
| 0.2052 | 1.34 | 2100 | 0.1317 | 0.94 |
|
| 108 |
+
| 0.1728 | 1.38 | 2150 | 0.1286 | 0.9533 |
|
| 109 |
+
| 0.1816 | 1.41 | 2200 | 0.1280 | 0.9333 |
|
| 110 |
+
| 0.1574 | 1.44 | 2250 | 0.1363 | 0.94 |
|
| 111 |
+
| 0.1907 | 1.47 | 2300 | 0.1229 | 0.9533 |
|
| 112 |
+
| 0.2032 | 1.5 | 2350 | 0.1036 | 0.96 |
|
| 113 |
+
| 0.1636 | 1.54 | 2400 | 0.1061 | 0.9533 |
|
| 114 |
+
| 0.1795 | 1.57 | 2450 | 0.1414 | 0.9333 |
|
| 115 |
+
| 0.1497 | 1.6 | 2500 | 0.1401 | 0.94 |
|
| 116 |
+
| 0.2026 | 1.63 | 2550 | 0.1462 | 0.9333 |
|
| 117 |
+
| 0.1797 | 1.66 | 2600 | 0.1355 | 0.9467 |
|
| 118 |
+
| 0.1612 | 1.7 | 2650 | 0.1283 | 0.9533 |
|
| 119 |
+
| 0.1922 | 1.73 | 2700 | 0.1235 | 0.9467 |
|
| 120 |
+
| 0.1321 | 1.76 | 2750 | 0.1336 | 0.9467 |
|
| 121 |
+
| 0.1908 | 1.79 | 2800 | 0.1518 | 0.94 |
|
| 122 |
+
| 0.1684 | 1.82 | 2850 | 0.1394 | 0.9533 |
|
| 123 |
+
| 0.1746 | 1.86 | 2900 | 0.1489 | 0.94 |
|
| 124 |
+
| 0.141 | 1.89 | 2950 | 0.1063 | 0.9667 |
|
| 125 |
+
| 0.1906 | 1.92 | 3000 | 0.1213 | 0.9467 |
|
| 126 |
+
| 0.1613 | 1.95 | 3050 | 0.1364 | 0.9467 |
|
| 127 |
+
| 0.2177 | 1.98 | 3100 | 0.1263 | 0.9533 |
|
| 128 |
+
| 0.1458 | 2.02 | 3150 | 0.1208 | 0.9533 |
|
| 129 |
+
| 0.1435 | 2.05 | 3200 | 0.1195 | 0.96 |
|
| 130 |
+
| 0.0988 | 2.08 | 3250 | 0.1282 | 0.96 |
|
| 131 |
+
| 0.1428 | 2.11 | 3300 | 0.1619 | 0.9467 |
|
| 132 |
+
| 0.1058 | 2.14 | 3350 | 0.1586 | 0.9467 |
|
| 133 |
+
| 0.149 | 2.18 | 3400 | 0.1502 | 0.9533 |
|
| 134 |
+
| 0.1188 | 2.21 | 3450 | 0.1954 | 0.9267 |
|
| 135 |
+
| 0.1482 | 2.24 | 3500 | 0.1797 | 0.94 |
|
| 136 |
+
| 0.1593 | 2.27 | 3550 | 0.1643 | 0.94 |
|
| 137 |
+
| 0.1543 | 2.3 | 3600 | 0.1505 | 0.94 |
|
| 138 |
+
| 0.1417 | 2.34 | 3650 | 0.1393 | 0.9467 |
|
| 139 |
+
| 0.1074 | 2.37 | 3700 | 0.1479 | 0.94 |
|
| 140 |
+
| 0.0966 | 2.4 | 3750 | 0.1819 | 0.9267 |
|
| 141 |
+
| 0.1114 | 2.43 | 3800 | 0.1515 | 0.94 |
|
| 142 |
+
| 0.1172 | 2.46 | 3850 | 0.1713 | 0.9467 |
|
| 143 |
+
| 0.0834 | 2.5 | 3900 | 0.1616 | 0.94 |
|
| 144 |
+
| 0.0987 | 2.53 | 3950 | 0.1986 | 0.9333 |
|
| 145 |
+
| 0.1317 | 2.56 | 4000 | 0.1889 | 0.94 |
|
| 146 |
+
| 0.1734 | 2.59 | 4050 | 0.1846 | 0.9533 |
|
| 147 |
+
| 0.1134 | 2.62 | 4100 | 0.1554 | 0.9333 |
|
| 148 |
+
| 0.1135 | 2.66 | 4150 | 0.1387 | 0.9533 |
|
| 149 |
+
| 0.1143 | 2.69 | 4200 | 0.1496 | 0.9533 |
|
| 150 |
+
| 0.1742 | 2.72 | 4250 | 0.1759 | 0.9467 |
|
| 151 |
+
| 0.1408 | 2.75 | 4300 | 0.1724 | 0.9333 |
|
| 152 |
+
| 0.1401 | 2.78 | 4350 | 0.1664 | 0.9467 |
|
| 153 |
+
| 0.1116 | 2.82 | 4400 | 0.1975 | 0.9267 |
|
| 154 |
+
| 0.131 | 2.85 | 4450 | 0.1730 | 0.9467 |
|
| 155 |
+
| 0.1236 | 2.88 | 4500 | 0.1504 | 0.9533 |
|
| 156 |
+
| 0.1501 | 2.91 | 4550 | 0.1554 | 0.9533 |
|
| 157 |
+
| 0.1609 | 2.94 | 4600 | 0.1642 | 0.9467 |
|
| 158 |
+
| 0.1443 | 2.98 | 4650 | 0.2157 | 0.92 |
|
| 159 |
+
| 0.1233 | 3.01 | 4700 | 0.1900 | 0.9333 |
|
| 160 |
+
| 0.1171 | 3.04 | 4750 | 0.1507 | 0.9333 |
|
| 161 |
+
| 0.0639 | 3.07 | 4800 | 0.2017 | 0.9333 |
|
| 162 |
+
| 0.0935 | 3.1 | 4850 | 0.1952 | 0.94 |
|
| 163 |
+
| 0.088 | 3.13 | 4900 | 0.2251 | 0.9333 |
|
| 164 |
+
| 0.0957 | 3.17 | 4950 | 0.1842 | 0.9533 |
|
| 165 |
+
| 0.1002 | 3.2 | 5000 | 0.1668 | 0.9467 |
|
| 166 |
+
| 0.0882 | 3.23 | 5050 | 0.1685 | 0.94 |
|
| 167 |
+
| 0.0579 | 3.26 | 5100 | 0.1653 | 0.9467 |
|
| 168 |
+
| 0.0912 | 3.29 | 5150 | 0.1735 | 0.9467 |
|
| 169 |
+
| 0.0811 | 3.33 | 5200 | 0.1832 | 0.9467 |
|
| 170 |
+
| 0.1104 | 3.36 | 5250 | 0.1755 | 0.9533 |
|
| 171 |
+
| 0.0785 | 3.39 | 5300 | 0.2030 | 0.9467 |
|
| 172 |
+
| 0.083 | 3.42 | 5350 | 0.1944 | 0.94 |
|
| 173 |
+
| 0.0769 | 3.45 | 5400 | 0.2107 | 0.94 |
|
| 174 |
+
| 0.0877 | 3.49 | 5450 | 0.1847 | 0.9467 |
|
| 175 |
+
| 0.083 | 3.52 | 5500 | 0.1751 | 0.9467 |
|
| 176 |
+
| 0.1179 | 3.55 | 5550 | 0.1765 | 0.9467 |
|
| 177 |
+
| 0.0965 | 3.58 | 5600 | 0.1905 | 0.94 |
|
| 178 |
+
| 0.0648 | 3.61 | 5650 | 0.2025 | 0.9333 |
|
| 179 |
+
| 0.0735 | 3.65 | 5700 | 0.2003 | 0.94 |
|
| 180 |
+
| 0.0857 | 3.68 | 5750 | 0.2074 | 0.94 |
|
| 181 |
+
| 0.0782 | 3.71 | 5800 | 0.1889 | 0.9467 |
|
| 182 |
+
| 0.0851 | 3.74 | 5850 | 0.1929 | 0.9533 |
|
| 183 |
+
| 0.0979 | 3.77 | 5900 | 0.2160 | 0.9333 |
|
| 184 |
+
| 0.0727 | 3.81 | 5950 | 0.2180 | 0.9333 |
|
| 185 |
+
| 0.1098 | 3.84 | 6000 | 0.1844 | 0.9467 |
|
| 186 |
+
| 0.0828 | 3.87 | 6050 | 0.1925 | 0.94 |
|
| 187 |
+
| 0.0865 | 3.9 | 6100 | 0.1895 | 0.9467 |
|
| 188 |
+
| 0.07 | 3.93 | 6150 | 0.1910 | 0.9467 |
|
| 189 |
+
| 0.0984 | 3.97 | 6200 | 0.1954 | 0.9467 |
|
| 190 |
+
| 0.1123 | 4.0 | 6250 | 0.2012 | 0.94 |
|
| 191 |
+
| 0.0674 | 4.03 | 6300 | 0.1938 | 0.94 |
|
| 192 |
+
| 0.1234 | 4.06 | 6350 | 0.2086 | 0.94 |
|
| 193 |
+
| 0.0599 | 4.09 | 6400 | 0.2169 | 0.9333 |
|
| 194 |
+
| 0.0603 | 4.13 | 6450 | 0.2116 | 0.94 |
|
| 195 |
+
| 0.0411 | 4.16 | 6500 | 0.2072 | 0.94 |
|
| 196 |
+
| 0.0784 | 4.19 | 6550 | 0.1993 | 0.9533 |
|
| 197 |
+
| 0.0891 | 4.22 | 6600 | 0.2086 | 0.94 |
|
| 198 |
+
| 0.076 | 4.25 | 6650 | 0.2058 | 0.9333 |
|
| 199 |
+
| 0.0653 | 4.29 | 6700 | 0.2164 | 0.9333 |
|
| 200 |
+
| 0.062 | 4.32 | 6750 | 0.2278 | 0.9333 |
|
| 201 |
+
| 0.0687 | 4.35 | 6800 | 0.2284 | 0.9333 |
|
| 202 |
+
| 0.0575 | 4.38 | 6850 | 0.2424 | 0.9333 |
|
| 203 |
+
| 0.0651 | 4.41 | 6900 | 0.2340 | 0.9333 |
|
| 204 |
+
| 0.0633 | 4.45 | 6950 | 0.2346 | 0.9333 |
|
| 205 |
+
| 0.109 | 4.48 | 7000 | 0.2319 | 0.9333 |
|
| 206 |
+
| 0.1 | 4.51 | 7050 | 0.2254 | 0.9333 |
|
| 207 |
+
| 0.085 | 4.54 | 7100 | 0.2141 | 0.9333 |
|
| 208 |
+
| 0.068 | 4.57 | 7150 | 0.2154 | 0.94 |
|
| 209 |
+
| 0.0852 | 4.61 | 7200 | 0.2206 | 0.94 |
|
| 210 |
+
| 0.0821 | 4.64 | 7250 | 0.2186 | 0.9333 |
|
| 211 |
+
| 0.0712 | 4.67 | 7300 | 0.2263 | 0.9333 |
|
| 212 |
+
| 0.0419 | 4.7 | 7350 | 0.2256 | 0.9333 |
|
| 213 |
+
| 0.0601 | 4.73 | 7400 | 0.2271 | 0.9333 |
|
| 214 |
+
| 0.0597 | 4.77 | 7450 | 0.2276 | 0.9333 |
|
| 215 |
+
| 0.0689 | 4.8 | 7500 | 0.2260 | 0.94 |
|
| 216 |
+
| 0.0437 | 4.83 | 7550 | 0.2261 | 0.9333 |
|
| 217 |
+
| 0.0636 | 4.86 | 7600 | 0.2289 | 0.9333 |
|
| 218 |
+
| 0.0982 | 4.89 | 7650 | 0.2302 | 0.9333 |
|
| 219 |
+
| 0.0392 | 4.93 | 7700 | 0.2316 | 0.9333 |
|
| 220 |
+
| 0.0438 | 4.96 | 7750 | 0.2311 | 0.9333 |
|
| 221 |
+
| 0.0753 | 4.99 | 7800 | 0.2309 | 0.9333 |
|
| 222 |
+
|
| 223 |
+
|
| 224 |
+
### Framework versions
|
| 225 |
+
|
| 226 |
+
- Transformers 4.23.1
|
| 227 |
+
- Pytorch 1.13.0
|
| 228 |
+
- Datasets 2.6.1
|
| 229 |
+
- Tokenizers 0.13.1
|