|
--- |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert-reg-biencoder-cosine_embedding |
|
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-reg-biencoder-cosine_embedding |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4608 |
|
- Mse: 0.2163 |
|
- Mae: 0.3729 |
|
- Pearson Corr: 0.1820 |
|
- Spearman Corr: 0.1619 |
|
- Cosine Sim: 0.6941 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | Pearson Corr | Spearman Corr | Cosine Sim | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------------:|:-------------:|:----------:| |
|
| 0.5366 | 1.0 | 21 | 0.5212 | 0.1367 | 0.2918 | 0.1078 | 0.1049 | 0.9047 | |
|
| 0.5294 | 2.0 | 42 | 0.5061 | 0.0996 | 0.2390 | 0.1385 | 0.1515 | 0.9048 | |
|
| 0.4811 | 3.0 | 63 | 0.4862 | 0.0855 | 0.2381 | 0.1325 | 0.0899 | 0.8857 | |
|
| 0.4292 | 4.0 | 84 | 0.4494 | 0.1511 | 0.3202 | 0.2155 | 0.1778 | 0.7872 | |
|
| 0.3672 | 5.0 | 105 | 0.4513 | 0.1470 | 0.3067 | 0.2206 | 0.1849 | 0.7980 | |
|
| 0.3259 | 6.0 | 126 | 0.4644 | 0.2209 | 0.3901 | 0.1864 | 0.1662 | 0.6696 | |
|
| 0.2866 | 7.0 | 147 | 0.4608 | 0.2163 | 0.3729 | 0.1820 | 0.1619 | 0.6941 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
