---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xlnet-base-mnli-fer-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. -->

# xlnet-base-mnli-fer-finetuned

This model is a fine-tuned version of [clevrly/xlnet-base-mnli-finetuned](https://huggingface.co/clevrly/xlnet-base-mnli-finetuned) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0152
- Accuracy: 0.7794

## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.5828        | 1.0   | 2219  | 0.9689          | 0.7277   |
| 0.578         | 2.0   | 4438  | 1.1408          | 0.7310   |
| 0.5027        | 3.0   | 6657  | 0.9754          | 0.7742   |
| 0.4233        | 4.0   | 8876  | 1.0719          | 0.7751   |
| 0.3026        | 5.0   | 11095 | 1.0152          | 0.7794   |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1