|
--- |
|
license: mit |
|
base_model: FacebookAI/roberta-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: RoBERTa_EmpAI_FineTuned |
|
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. --> |
|
|
|
# RoBERTa_EmpAI_FineTuned |
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0707 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 483 | 7.4258 | |
|
| 12.6437 | 2.0 | 967 | 2.1112 | |
|
| 4.9019 | 3.0 | 1450 | 0.0872 | |
|
| 0.4036 | 4.0 | 1934 | 0.0765 | |
|
| 0.0802 | 4.99 | 2415 | 0.0754 | |
|
| 0.0737 | 6.0 | 2898 | 0.0708 | |
|
| 0.0749 | 7.0 | 3382 | 0.0705 | |
|
| 0.0712 | 8.0 | 3865 | 0.0702 | |
|
| 0.0708 | 9.0 | 4349 | 0.0692 | |
|
| 0.0698 | 9.99 | 4830 | 0.0696 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|