---
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-large_sst2_sp0_ar0
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: glue
      type: glue
      config: sst2
      split: validation
      args: sst2
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9560546875
---

<!-- 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-large_sst2_sp0_ar0

This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3456
- Accuracy: 0.9561

## 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: 16
- eval_batch_size: 32
- seed: 1
- distributed_type: tpu
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- training_steps: 750

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6852        | 0.01  | 25   | 0.6952          | 0.5092   |
| 0.6751        | 0.01  | 50   | 0.6331          | 0.7546   |
| 0.603         | 0.02  | 75   | 0.4811          | 0.8899   |
| 0.3459        | 0.02  | 100  | 0.2048          | 0.9335   |
| 0.1808        | 0.03  | 125  | 0.2377          | 0.9300   |
| 0.1933        | 0.04  | 150  | 0.3369          | 0.9323   |
| 0.527         | 0.04  | 175  | 0.6582          | 0.9404   |
| 0.2241        | 0.05  | 200  | 0.1874          | 0.9507   |
| 0.1997        | 0.05  | 225  | 0.5160          | 0.9472   |
| 0.2192        | 0.06  | 250  | 0.5193          | 0.9461   |
| 0.168         | 0.07  | 275  | 0.4091          | 0.9484   |
| 0.1879        | 0.07  | 300  | 0.3114          | 0.9427   |
| 0.1653        | 0.08  | 325  | 0.5526          | 0.9484   |
| 0.1847        | 0.08  | 350  | 0.6536          | 0.9450   |
| 0.1449        | 0.09  | 375  | 0.6520          | 0.9438   |
| 0.2485        | 0.1   | 400  | 0.4093          | 0.9518   |
| 0.1604        | 0.1   | 425  | 0.2821          | 0.9461   |
| 0.1316        | 0.11  | 450  | 0.8609          | 0.9461   |
| 0.1754        | 0.11  | 475  | 0.4047          | 0.9472   |
| 0.1524        | 0.12  | 500  | 0.4034          | 0.9495   |
| 0.4571        | 0.13  | 525  | 0.2895          | 0.9495   |
| 0.1448        | 0.13  | 550  | 0.5239          | 0.9484   |
| 0.1459        | 0.14  | 575  | 0.2996          | 0.9518   |
| 0.2131        | 0.14  | 600  | 0.2983          | 0.9495   |
| 0.1298        | 0.15  | 625  | 0.5322          | 0.9484   |
| 0.1519        | 0.16  | 650  | 0.5311          | 0.9518   |
| 0.1809        | 0.16  | 675  | 0.5271          | 0.9495   |
| 0.1495        | 0.17  | 700  | 0.5282          | 0.9495   |
| 0.1665        | 0.17  | 725  | 0.5307          | 0.9507   |
| 0.1978        | 0.18  | 750  | 0.5295          | 0.9507   |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.0+cu118
- Datasets 2.14.5
- Tokenizers 0.11.6