bert_tiny_lda_50_v1_book
This model is a fine-tuned version of on the gokulsrinivasagan/processed_book_corpus-ld-50 dataset. It achieves the following results on the evaluation set:
- Loss: 4.4767
- Accuracy: 0.6768
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: 0.0001
- train_batch_size: 160
- eval_batch_size: 160
- seed: 10
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 9.5487 | 0.7025 | 10000 | 9.3862 | 0.1643 |
| 6.4629 | 1.4051 | 20000 | 5.9991 | 0.4932 |
| 5.845 | 2.1076 | 30000 | 5.4385 | 0.5587 |
| 5.564 | 2.8102 | 40000 | 5.1861 | 0.5911 |
| 5.4009 | 3.5127 | 50000 | 5.0364 | 0.6107 |
| 5.2879 | 4.2153 | 60000 | 4.9377 | 0.6221 |
| 5.2055 | 4.9178 | 70000 | 4.8482 | 0.6306 |
| 5.1368 | 5.6203 | 80000 | 4.7866 | 0.6365 |
| 5.0913 | 6.3229 | 90000 | 4.7452 | 0.6414 |
| 5.0527 | 7.0254 | 100000 | 4.7075 | 0.6454 |
| 5.0258 | 7.7280 | 110000 | 4.6830 | 0.6489 |
| 4.9991 | 8.4305 | 120000 | 4.6571 | 0.6519 |
| 4.9708 | 9.1331 | 130000 | 4.6426 | 0.6542 |
| 4.9566 | 9.8356 | 140000 | 4.6210 | 0.6573 |
| 4.9396 | 10.5381 | 150000 | 4.6070 | 0.6589 |
| 4.929 | 11.2407 | 160000 | 4.5963 | 0.6604 |
| 4.9134 | 11.9432 | 170000 | 4.5835 | 0.6622 |
| 4.901 | 12.6458 | 180000 | 4.5683 | 0.6639 |
| 4.8884 | 13.3483 | 190000 | 4.5644 | 0.6646 |
| 4.8823 | 14.0509 | 200000 | 4.5529 | 0.6661 |
| 4.8706 | 14.7534 | 210000 | 4.5440 | 0.6672 |
| 4.8607 | 15.4560 | 220000 | 4.5351 | 0.6688 |
| 4.8551 | 16.1585 | 230000 | 4.5289 | 0.6691 |
| 4.8461 | 16.8610 | 240000 | 4.5238 | 0.6702 |
| 4.8365 | 17.5636 | 250000 | 4.5181 | 0.6708 |
| 4.831 | 18.2661 | 260000 | 4.5125 | 0.6716 |
| 4.8298 | 18.9687 | 270000 | 4.5080 | 0.6724 |
| 4.82 | 19.6712 | 280000 | 4.5026 | 0.6732 |
| 4.8168 | 20.3738 | 290000 | 4.4968 | 0.6738 |
| 4.8087 | 21.0763 | 300000 | 4.4940 | 0.6745 |
| 4.8065 | 21.7788 | 310000 | 4.4873 | 0.6753 |
| 4.7999 | 22.4814 | 320000 | 4.4847 | 0.6755 |
| 4.798 | 23.1839 | 330000 | 4.4818 | 0.6759 |
| 4.7951 | 23.8865 | 340000 | 4.4781 | 0.6764 |
| 4.7946 | 24.5890 | 350000 | 4.4755 | 0.6768 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1