|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- gokuls/wiki_book_corpus_complete_processed_bert_dataset |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: HBERTv1_emb_compress_48_L10_H512_A8 |
|
results: |
|
- task: |
|
name: Masked Language Modeling |
|
type: fill-mask |
|
dataset: |
|
name: gokuls/wiki_book_corpus_complete_processed_bert_dataset |
|
type: gokuls/wiki_book_corpus_complete_processed_bert_dataset |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.17367944889882433 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# HBERTv1_emb_compress_48_L10_H512_A8 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.7680 |
|
- Accuracy: 0.1737 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 56 |
|
- eval_batch_size: 56 |
|
- seed: 10 |
|
- distributed_type: multi-GPU |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 10000 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:------:|:---------------:|:--------:| |
|
| 7.1035 | 0.1 | 10000 | 7.0837 | 0.0844 | |
|
| 6.6799 | 0.19 | 20000 | 6.6737 | 0.1072 | |
|
| 6.5327 | 0.29 | 30000 | 6.5279 | 0.1194 | |
|
| 6.4362 | 0.38 | 40000 | 6.4358 | 0.1272 | |
|
| 6.3648 | 0.48 | 50000 | 6.3700 | 0.1335 | |
|
| 6.3181 | 0.57 | 60000 | 6.3158 | 0.1355 | |
|
| 6.2776 | 0.67 | 70000 | 6.2769 | 0.1380 | |
|
| 6.2469 | 0.76 | 80000 | 6.2438 | 0.1400 | |
|
| 6.218 | 0.86 | 90000 | 6.2187 | 0.1422 | |
|
| 6.2036 | 0.96 | 100000 | 6.1963 | 0.1434 | |
|
| 6.1806 | 1.05 | 110000 | 6.1776 | 0.1451 | |
|
| 6.1591 | 1.15 | 120000 | 6.1621 | 0.1456 | |
|
| 6.1503 | 1.24 | 130000 | 6.1473 | 0.1468 | |
|
| 6.1391 | 1.34 | 140000 | 6.1357 | 0.1466 | |
|
| 6.126 | 1.43 | 150000 | 6.1230 | 0.1477 | |
|
| 6.1145 | 1.53 | 160000 | 6.1133 | 0.1479 | |
|
| 6.1067 | 1.62 | 170000 | 6.1040 | 0.1486 | |
|
| 6.097 | 1.72 | 180000 | 6.0966 | 0.1488 | |
|
| 6.0825 | 1.82 | 190000 | 6.0875 | 0.1492 | |
|
| 6.0783 | 1.91 | 200000 | 6.0797 | 0.1494 | |
|
| 6.0673 | 2.01 | 210000 | 6.0730 | 0.1499 | |
|
| 6.066 | 2.1 | 220000 | 6.0623 | 0.1501 | |
|
| 6.0534 | 2.2 | 230000 | 6.0510 | 0.1504 | |
|
| 6.0004 | 2.29 | 240000 | 5.9972 | 0.1517 | |
|
| 5.9609 | 2.39 | 250000 | 5.9492 | 0.1530 | |
|
| 5.93 | 2.49 | 260000 | 5.9169 | 0.1551 | |
|
| 5.9058 | 2.58 | 270000 | 5.8895 | 0.1571 | |
|
| 5.8834 | 2.68 | 280000 | 5.8618 | 0.1597 | |
|
| 5.8572 | 2.77 | 290000 | 5.8394 | 0.1623 | |
|
| 5.8296 | 2.87 | 300000 | 5.8168 | 0.1661 | |
|
| 5.8085 | 2.96 | 310000 | 5.7926 | 0.1703 | |
|
| 5.7873 | 3.06 | 320000 | 5.7663 | 0.1739 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 1.14.0a0+410ce96 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
