|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- gokulsrinivasagan/processed_book_corpus-ld |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert_base_train_book_v2 |
|
results: |
|
- task: |
|
name: Masked Language Modeling |
|
type: fill-mask |
|
dataset: |
|
name: gokulsrinivasagan/processed_book_corpus-ld |
|
type: gokulsrinivasagan/processed_book_corpus-ld |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.7300233078924688 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distilbert_base_train_book_v2 |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co./distilbert-base-uncased) on the gokulsrinivasagan/processed_book_corpus-ld dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2024 |
|
- Accuracy: 0.7300 |
|
|
|
## 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 | |
|
|:-------------:|:-------:|:------:|:---------------:|:--------:| |
|
| 5.604 | 0.7025 | 10000 | 5.4504 | 0.1650 | |
|
| 4.6179 | 1.4051 | 20000 | 3.8277 | 0.3758 | |
|
| 2.353 | 2.1076 | 30000 | 2.0408 | 0.5933 | |
|
| 2.0739 | 2.8102 | 40000 | 1.7932 | 0.6316 | |
|
| 1.9345 | 3.5127 | 50000 | 1.6618 | 0.6527 | |
|
| 1.844 | 4.2153 | 60000 | 1.5829 | 0.6653 | |
|
| 1.7874 | 4.9178 | 70000 | 1.5248 | 0.6750 | |
|
| 1.737 | 5.6203 | 80000 | 1.4824 | 0.6819 | |
|
| 1.7017 | 6.3229 | 90000 | 1.4506 | 0.6876 | |
|
| 1.6703 | 7.0254 | 100000 | 1.4204 | 0.6921 | |
|
| 1.6497 | 7.7280 | 110000 | 1.3988 | 0.6961 | |
|
| 1.6245 | 8.4305 | 120000 | 1.3766 | 0.6996 | |
|
| 1.6015 | 9.1331 | 130000 | 1.3628 | 0.7019 | |
|
| 1.5882 | 9.8356 | 140000 | 1.3451 | 0.7052 | |
|
| 1.5738 | 10.5381 | 150000 | 1.3310 | 0.7076 | |
|
| 1.563 | 11.2407 | 160000 | 1.3214 | 0.7091 | |
|
| 1.5473 | 11.9432 | 170000 | 1.3087 | 0.7113 | |
|
| 1.5364 | 12.6458 | 180000 | 1.2944 | 0.7135 | |
|
| 1.5257 | 13.3483 | 190000 | 1.2905 | 0.7146 | |
|
| 1.5164 | 14.0509 | 200000 | 1.2789 | 0.7161 | |
|
| 1.5071 | 14.7534 | 210000 | 1.2702 | 0.7176 | |
|
| 1.4972 | 15.4560 | 220000 | 1.2618 | 0.7193 | |
|
| 1.4915 | 16.1585 | 230000 | 1.2573 | 0.7201 | |
|
| 1.4824 | 16.8610 | 240000 | 1.2515 | 0.7211 | |
|
| 1.4748 | 17.5636 | 250000 | 1.2450 | 0.7223 | |
|
| 1.4686 | 18.2661 | 260000 | 1.2389 | 0.7234 | |
|
| 1.4649 | 18.9687 | 270000 | 1.2333 | 0.7243 | |
|
| 1.4566 | 19.6712 | 280000 | 1.2285 | 0.7253 | |
|
| 1.4529 | 20.3738 | 290000 | 1.2230 | 0.7261 | |
|
| 1.4451 | 21.0763 | 300000 | 1.2189 | 0.7269 | |
|
| 1.443 | 21.7788 | 310000 | 1.2136 | 0.7278 | |
|
| 1.4357 | 22.4814 | 320000 | 1.2100 | 0.7284 | |
|
| 1.4327 | 23.1839 | 330000 | 1.2068 | 0.7290 | |
|
| 1.4309 | 23.8865 | 340000 | 1.2040 | 0.7295 | |
|
| 1.4281 | 24.5890 | 350000 | 1.2005 | 0.7300 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.1 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.1 |
|
|
