---
license: apache-2.0
base_model: lukeleeai/t5-base_cola_densedense_baseline
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-base_cola_dense_mare_mlp_einsum
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: glue
      type: glue
      config: cola
      split: validation
      args: cola
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.7526366251198466
---

<!-- 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_dense_mare_mlp_einsum

This model is a fine-tuned version of [lukeleeai/t5-base_cola_densedense_baseline](https://huggingface.co/lukeleeai/t5-base_cola_densedense_baseline) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6369
- Accuracy: 0.7526

## 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: 8
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5857        | 0.19  | 50   | 0.6136          | 0.6913   |
| 0.5918        | 0.37  | 100  | 0.6222          | 0.6913   |
| 0.5688        | 0.56  | 150  | 0.6246          | 0.6913   |
| 0.685         | 0.75  | 200  | 0.6150          | 0.6913   |
| 0.565         | 0.93  | 250  | 0.6197          | 0.6913   |
| 0.5892        | 1.12  | 300  | 0.6066          | 0.6922   |
| 0.5444        | 1.31  | 350  | 0.5988          | 0.7009   |
| 0.6097        | 1.5   | 400  | 0.5796          | 0.7076   |
| 0.5904        | 1.68  | 450  | 0.5916          | 0.6884   |
| 0.5898        | 1.87  | 500  | 0.5815          | 0.7057   |
| 0.5569        | 2.06  | 550  | 0.5771          | 0.6999   |
| 0.4553        | 2.24  | 600  | 0.6217          | 0.7210   |
| 0.4796        | 2.43  | 650  | 0.6323          | 0.7229   |
| 0.5362        | 2.62  | 700  | 0.6491          | 0.7229   |
| 0.5756        | 2.8   | 750  | 0.5745          | 0.7018   |
| 0.5731        | 2.99  | 800  | 0.6104          | 0.7315   |
| 0.4573        | 3.18  | 850  | 0.6087          | 0.7248   |
| 0.5395        | 3.36  | 900  | 0.6768          | 0.7459   |
| 0.4447        | 3.55  | 950  | 0.6372          | 0.7383   |
| 0.3891        | 3.74  | 1000 | 0.6589          | 0.7402   |
| 0.3923        | 3.93  | 1050 | 0.6273          | 0.7344   |
| 0.3855        | 4.11  | 1100 | 0.7189          | 0.7344   |
| 0.4015        | 4.3   | 1150 | 0.6456          | 0.7469   |
| 0.33          | 4.49  | 1200 | 0.7179          | 0.7450   |
| 0.354         | 4.67  | 1250 | 0.6369          | 0.7526   |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.11.6