|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/bert_uncased_L-4_H-512_A-8 |
|
model-index: |
|
- name: bert_uncased_L-4_H-512_A-8-finetuned-eurlex-longer |
|
results: [] |
|
--- |
|
|
|
<!-- 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_uncased_L-4_H-512_A-8-finetuned-eurlex-longer |
|
|
|
This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8229 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.0308 | 1.0 | 3913 | 0.9303 | |
|
| 1.0053 | 2.0 | 7826 | 0.9066 | |
|
| 0.9799 | 3.0 | 11739 | 0.8795 | |
|
| 0.9575 | 4.0 | 15652 | 0.8677 | |
|
| 0.9413 | 5.0 | 19565 | 0.8555 | |
|
| 0.9319 | 6.0 | 23478 | 0.8447 | |
|
| 0.9235 | 7.0 | 27391 | 0.8388 | |
|
| 0.9132 | 8.0 | 31304 | 0.8345 | |
|
| 0.9105 | 9.0 | 35217 | 0.8312 | |
|
| 0.9154 | 10.0 | 39130 | 0.8229 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.1 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
