---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
base_model: google/canine-c
model-index:
- name: canine-c-finetuned-sst2
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: glue
      type: glue
      args: sst2
    metrics:
    - type: accuracy
      value: 0.8486238532110092
      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. -->

# canine-c-finetuned-sst2

This model is a fine-tuned version of [google/canine-c](https://huggingface.co/google/canine-c) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6025
- Accuracy: 0.8486

## 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: 4.9121586874695155e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3415        | 1.0   | 2105 | 0.4196          | 0.8280   |
| 0.2265        | 2.0   | 4210 | 0.4924          | 0.8211   |
| 0.1439        | 3.0   | 6315 | 0.5726          | 0.8337   |
| 0.0974        | 4.0   | 8420 | 0.6025          | 0.8486   |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6