|
--- |
|
library_name: peft |
|
license: mit |
|
base_model: FaceBookAI/roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: Lora_model2 |
|
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. --> |
|
|
|
# Sharpaxis/RoBERTa_Movie_Review_LoRA |
|
|
|
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: 0.3046 |
|
- F1: 0.8737 |
|
- Acc: 0.8734 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Acc | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:| |
|
| 0.5074 | 1.0 | 534 | 0.3279 | 0.8635 | 0.8565 | |
|
| 0.3222 | 2.0 | 1068 | 0.3106 | 0.8742 | 0.8771 | |
|
| 0.3153 | 3.0 | 1602 | 0.3046 | 0.8737 | 0.8734 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.14.0 |
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.1 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
