pretrained-bert
This model is a fine-tuned version of on the cc_news dataset. It achieves the following results on the evaluation set:
- Loss: 5.7000
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.1956 | 0.08 | 1000 | 7.0109 |
| 6.9483 | 0.17 | 2000 | 6.8538 |
| 6.8304 | 0.25 | 3000 | 6.7408 |
| 6.7429 | 0.33 | 4000 | 6.6812 |
| 6.6812 | 0.42 | 5000 | 6.6208 |
| 6.6102 | 0.5 | 6000 | 6.5837 |
| 6.5974 | 0.58 | 7000 | 6.5340 |
| 6.54 | 0.67 | 8000 | 6.5080 |
| 6.5184 | 0.75 | 9000 | 6.4795 |
| 6.4937 | 0.83 | 10000 | 6.4346 |
| 6.4671 | 0.92 | 11000 | 6.4364 |
| 6.4347 | 1.0 | 12000 | 6.4180 |
| 6.3966 | 1.08 | 13000 | 6.4009 |
| 6.3911 | 1.17 | 14000 | 6.3625 |
| 6.3594 | 1.25 | 15000 | 6.3390 |
| 6.3437 | 1.33 | 16000 | 6.3383 |
| 6.2964 | 1.42 | 17000 | 6.2872 |
| 6.3101 | 1.5 | 18000 | 6.2789 |
| 6.3023 | 1.58 | 19000 | 6.2913 |
| 6.2916 | 1.67 | 20000 | 6.2443 |
| 6.2647 | 1.75 | 21000 | 6.2324 |
| 6.2418 | 1.83 | 22000 | 6.2291 |
| 6.2432 | 1.92 | 23000 | 6.2088 |
| 6.2269 | 2.0 | 24000 | 6.1954 |
| 6.1794 | 2.08 | 25000 | 6.1979 |
| 6.1813 | 2.17 | 26000 | 6.1586 |
| 6.186 | 2.25 | 27000 | 6.1581 |
| 6.1497 | 2.33 | 28000 | 6.1378 |
| 6.1253 | 2.42 | 29000 | 6.1364 |
| 6.1278 | 2.5 | 30000 | 6.1096 |
| 6.0937 | 2.58 | 31000 | 6.0842 |
| 6.0982 | 2.67 | 32000 | 6.0802 |
| 6.0834 | 2.75 | 33000 | 6.0576 |
| 6.0595 | 2.83 | 34000 | 6.0290 |
| 6.0427 | 2.92 | 35000 | 6.0079 |
| 6.0553 | 3.0 | 36000 | 6.0322 |
| 5.9979 | 3.08 | 37000 | 5.9859 |
| 5.9882 | 3.17 | 38000 | 5.9754 |
| 5.9933 | 3.25 | 39000 | 5.9619 |
| 5.9599 | 3.33 | 40000 | 5.9738 |
| 5.9597 | 3.42 | 41000 | 5.9464 |
| 5.95 | 3.5 | 42000 | 5.9281 |
| 5.9613 | 3.58 | 43000 | 5.9190 |
| 5.9362 | 3.67 | 44000 | 5.9000 |
| 5.9186 | 3.75 | 45000 | 5.8801 |
| 5.9263 | 3.83 | 46000 | 5.8398 |
| 5.8747 | 3.92 | 47000 | 5.8371 |
| 5.8566 | 4.0 | 48000 | 5.8147 |
| 5.8434 | 4.08 | 49000 | 5.8102 |
| 5.8194 | 4.17 | 50000 | 5.7867 |
| 5.8467 | 4.25 | 51000 | 5.7718 |
| 5.8149 | 4.33 | 52000 | 5.7629 |
| 5.7929 | 4.42 | 53000 | 5.7506 |
| 5.7763 | 4.5 | 54000 | 5.7356 |
| 5.7757 | 4.58 | 55000 | 5.7236 |
| 5.7624 | 4.67 | 56000 | 5.6957 |
| 5.7464 | 4.75 | 57000 | 5.7163 |
| 5.778 | 4.83 | 58000 | 5.7008 |
| 5.7322 | 4.92 | 59000 | 5.6870 |
| 5.7392 | 5.0 | 60000 | 5.7000 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 4