---
license: apache-2.0
base_model: google/bert_uncased_L-2_H-256_A-4
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: bert_uncased_L-2_H-256_A-4_emotion
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: emotion
      type: emotion
      config: split
      split: validation
      args: split
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9205
---

<!-- 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. -->

# bert_uncased_L-2_H-256_A-4_emotion

This model is a fine-tuned version of [google/bert_uncased_L-2_H-256_A-4](https://huggingface.co/google/bert_uncased_L-2_H-256_A-4) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2109
- Accuracy: 0.9205

## 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: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3021        | 1.0   | 250  | 0.8220          | 0.7345   |
| 0.6139        | 2.0   | 500  | 0.3995          | 0.885    |
| 0.3573        | 3.0   | 750  | 0.2846          | 0.902    |
| 0.261         | 4.0   | 1000 | 0.2471          | 0.9085   |
| 0.2206        | 5.0   | 1250 | 0.2270          | 0.914    |
| 0.1952        | 6.0   | 1500 | 0.2247          | 0.9125   |
| 0.1757        | 7.0   | 1750 | 0.2127          | 0.918    |
| 0.1679        | 8.0   | 2000 | 0.2131          | 0.9145   |
| 0.1507        | 9.0   | 2250 | 0.2109          | 0.9205   |
| 0.1514        | 10.0  | 2500 | 0.2111          | 0.92     |


### Framework versions

- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1