|
--- |
|
language: |
|
- en |
|
base_model: FacebookAI/roberta-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: MNLI |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE MNLI |
|
type: glue |
|
args: mnli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8977827502034175 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# MNLI |
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the GLUE MNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6192 |
|
- Accuracy: 0.8978 |
|
|
|
## 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 | Accuracy | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:--------:|:---------------:| |
|
| 0.3135 | 1.0 | 6136 | 0.8872 | 0.3194 | |
|
| 0.2281 | 2.0 | 12272 | 0.8983 | 0.3009 | |
|
| 0.1484 | 3.0 | 18408 | 0.9007 | 0.3358 | |
|
| 0.0955 | 4.0 | 24544 | 0.8995 | 0.4247 | |
|
| 0.0616 | 5.0 | 30680 | 0.4938 | 0.8983 | |
|
| 0.0441 | 6.0 | 36816 | 0.6055 | 0.9009 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.3 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
