|
--- |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- gokulsrinivasagan/processed_book_corpus-ld-5 |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert_tiny_lda_5_v1_book |
|
results: |
|
- task: |
|
name: Masked Language Modeling |
|
type: fill-mask |
|
dataset: |
|
name: gokulsrinivasagan/processed_book_corpus-ld-5 |
|
type: gokulsrinivasagan/processed_book_corpus-ld-5 |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.6857676426031905 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bert_tiny_lda_5_v1_book |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the gokulsrinivasagan/processed_book_corpus-ld-5 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.8600 |
|
- Accuracy: 0.6858 |
|
|
|
## 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 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 | |
|
|:-------------:|:-------:|:------:|:---------------:|:--------:| |
|
| 7.2508 | 0.7025 | 10000 | 7.0913 | 0.1639 | |
|
| 5.6868 | 1.4051 | 20000 | 5.0071 | 0.4074 | |
|
| 4.0487 | 2.1076 | 30000 | 3.6967 | 0.5617 | |
|
| 3.7657 | 2.8102 | 40000 | 3.4422 | 0.5989 | |
|
| 3.6336 | 3.5127 | 50000 | 3.3142 | 0.6176 | |
|
| 3.5449 | 4.2153 | 60000 | 3.2372 | 0.6291 | |
|
| 3.4893 | 4.9178 | 70000 | 3.1788 | 0.6376 | |
|
| 3.4397 | 5.6203 | 80000 | 3.1367 | 0.6442 | |
|
| 3.4066 | 6.3229 | 90000 | 3.1054 | 0.6491 | |
|
| 3.3758 | 7.0254 | 100000 | 3.0734 | 0.6534 | |
|
| 3.3548 | 7.7280 | 110000 | 3.0504 | 0.6571 | |
|
| 3.3302 | 8.4305 | 120000 | 3.0304 | 0.6599 | |
|
| 3.3087 | 9.1331 | 130000 | 3.0157 | 0.6620 | |
|
| 3.2942 | 9.8356 | 140000 | 2.9982 | 0.6654 | |
|
| 3.2799 | 10.5381 | 150000 | 2.9831 | 0.6672 | |
|
| 3.271 | 11.2407 | 160000 | 2.9750 | 0.6687 | |
|
| 3.2545 | 11.9432 | 170000 | 2.9624 | 0.6703 | |
|
| 3.2444 | 12.6458 | 180000 | 2.9493 | 0.6723 | |
|
| 3.2336 | 13.3483 | 190000 | 2.9428 | 0.6731 | |
|
| 3.2254 | 14.0509 | 200000 | 2.9316 | 0.6746 | |
|
| 3.2143 | 14.7534 | 210000 | 2.9231 | 0.6759 | |
|
| 3.2058 | 15.4560 | 220000 | 2.9154 | 0.6772 | |
|
| 3.2014 | 16.1585 | 230000 | 2.9095 | 0.6780 | |
|
| 3.1923 | 16.8610 | 240000 | 2.9047 | 0.6788 | |
|
| 3.1846 | 17.5636 | 250000 | 2.8982 | 0.6797 | |
|
| 3.1797 | 18.2661 | 260000 | 2.8922 | 0.6805 | |
|
| 3.1768 | 18.9687 | 270000 | 2.8886 | 0.6813 | |
|
| 3.1696 | 19.6712 | 280000 | 2.8828 | 0.6822 | |
|
| 3.1656 | 20.3738 | 290000 | 2.8787 | 0.6826 | |
|
| 3.1581 | 21.0763 | 300000 | 2.8756 | 0.6834 | |
|
| 3.1566 | 21.7788 | 310000 | 2.8690 | 0.6842 | |
|
| 3.1508 | 22.4814 | 320000 | 2.8671 | 0.6845 | |
|
| 3.1496 | 23.1839 | 330000 | 2.8648 | 0.6849 | |
|
| 3.1475 | 23.8865 | 340000 | 2.8612 | 0.6853 | |
|
| 3.1459 | 24.5890 | 350000 | 2.8586 | 0.6859 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.2.1+cu118 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.20.3 |
|
|
