dearkarina's picture
Upload RobertaForSequenceClassification
ae10871 verified
---
base_model: distilbert/distilroberta-base
datasets:
- financial_phrasebank
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: my_miniroberta_model
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: financial_phrasebank
type: financial_phrasebank
config: sentences_allagree
split: train
args: sentences_allagree
metrics:
- type: accuracy
value: 0.9713024282560706
name: Accuracy
---
<!-- 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. -->
# my_miniroberta_model
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the financial_phrasebank dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1663
- Accuracy: 0.9713
## 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: 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 227 | 0.2026 | 0.9338 |
| No log | 2.0 | 454 | 0.1337 | 0.9669 |
| 0.2375 | 3.0 | 681 | 0.1639 | 0.9713 |
| 0.2375 | 4.0 | 908 | 0.1499 | 0.9735 |
| 0.0176 | 5.0 | 1135 | 0.1663 | 0.9713 |
### Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1