---
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-base_cola_moe_ex38_sp0_2_ar0_0_mare_mlp
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: glue
      type: glue
      config: rte
      split: validation
      args: rte
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.0
---

<!-- 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. -->

# t5-base_cola_moe_ex38_sp0_2_ar0_0_mare_mlp

This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4611
- Accuracy: 0.0

## 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: 32
- eval_batch_size: 64
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 6

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5168        | 0.32  | 25   | 0.5669          | 0.7220   |
| 0.5033        | 0.64  | 50   | 0.5296          | 0.7690   |
| 0.4742        | 0.96  | 75   | 0.5493          | 0.7653   |
| 0.4217        | 1.28  | 100  | 0.5473          | 0.7726   |
| 0.4188        | 1.6   | 125  | 0.5759          | 0.7834   |
| 0.4565        | 1.92  | 150  | 0.5721          | 0.7653   |
| 0.3354        | 2.24  | 175  | 0.5307          | 0.7762   |
| 0.2589        | 2.56  | 200  | 0.5804          | 0.7942   |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.11.6