metadata
language:
- en
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: SST2
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE SST2
type: glue
args: sst2
metrics:
- name: Accuracy
type: accuracy
value: 0.9621559633027523
SST2
This model is a fine-tuned version of FacebookAI/roberta-large on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1664
- Accuracy: 0.9622
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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1696 | 1.0 | 1053 | 0.1285 | 0.9507 |
| 0.1166 | 2.0 | 2106 | 0.1410 | 0.9610 |
| 0.0865 | 3.0 | 3159 | 0.1355 | 0.9576 |
| 0.0637 | 4.0 | 4212 | 0.1412 | 0.9587 |
| 0.0468 | 5.0 | 5265 | 0.1664 | 0.9622 |
| 0.0335 | 6.0 | 6318 | 0.1930 | 0.9599 |
Framework versions
- Transformers 4.43.3
- Pytorch 1.11.0+cu113
- Datasets 2.20.0
- Tokenizers 0.19.1