|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: BERiT_2000_enriched |
|
|
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. --> |
|
|
|
|
|
# BERiT_2000_enriched |
|
|
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 6.6052 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 6.786 | 0.19 | 500 | 6.6797 | |
|
|
| 6.6441 | 0.39 | 1000 | 6.6574 | |
|
|
| 6.6376 | 0.58 | 1500 | 6.6240 | |
|
|
| 6.5951 | 0.77 | 2000 | 6.6291 | |
|
|
| 6.6123 | 0.97 | 2500 | 6.6355 | |
|
|
| 6.6028 | 1.16 | 3000 | 6.6084 | |
|
|
| 6.5974 | 1.36 | 3500 | 6.5984 | |
|
|
| 6.6104 | 1.55 | 4000 | 6.5775 | |
|
|
| 6.6113 | 1.74 | 4500 | 6.6062 | |
|
|
| 6.5895 | 1.94 | 5000 | 6.5931 | |
|
|
| 6.6106 | 2.13 | 5500 | 6.6276 | |
|
|
| 6.635 | 2.32 | 6000 | 6.5973 | |
|
|
| 6.5694 | 2.52 | 6500 | 6.6021 | |
|
|
| 6.612 | 2.71 | 7000 | 6.5882 | |
|
|
| 6.5984 | 2.9 | 7500 | 6.6052 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.24.0 |
|
|
- Pytorch 1.12.1+cu113 |
|
|
- Datasets 2.6.1 |
|
|
- Tokenizers 0.13.2 |
|
|
|
