---
library_name: transformers
license: apache-2.0
base_model: yigagilbert/t5_efficient_small_language_ID
tags:
- generated_from_trainer
datasets:
- generator
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: t5_small_language_Classification
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: generator
      type: generator
      config: default
      split: train
      args: default
    metrics:
    - type: accuracy
      value: 0.658879605381663
      name: Accuracy
    - type: precision
      value: 0.6928469419086497
      name: Precision
    - type: recall
      value: 0.658879605381663
      name: Recall
    - type: f1
      value: 0.6286369104782076
      name: F1
---

<!-- 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_small_language_Classification

This model is a fine-tuned version of [yigagilbert/t5_efficient_small_language_ID](https://huggingface.co/yigagilbert/t5_efficient_small_language_ID) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6482
- Accuracy: 0.6589
- Precision: 0.6928
- Recall: 0.6589
- F1: 0.6286

## 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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 1000
- training_steps: 60000

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.6453        | 0.0083 | 500  | 1.7792          | 0.5575   | 0.6272    | 0.5575 | 0.5283 |
| 0.3701        | 0.0167 | 1000 | 2.8566          | 0.4925   | 0.6309    | 0.4925 | 0.4427 |
| 0.3602        | 0.025  | 1500 | 3.4108          | 0.4331   | 0.6188    | 0.4331 | 0.3903 |
| 0.3573        | 0.0333 | 2000 | 1.9821          | 0.5855   | 0.6303    | 0.5855 | 0.5419 |
| 0.4229        | 0.0417 | 2500 | 1.9248          | 0.6071   | 0.6712    | 0.6071 | 0.5731 |
| 0.2156        | 0.05   | 3000 | 2.6673          | 0.5217   | 0.6906    | 0.5217 | 0.4851 |
| 0.3752        | 0.0583 | 3500 | 1.9381          | 0.5984   | 0.6682    | 0.5984 | 0.5619 |
| 0.4996        | 0.0667 | 4000 | 1.5622          | 0.6266   | 0.6757    | 0.6266 | 0.6022 |
| 0.2773        | 0.075  | 4500 | 1.8355          | 0.6299   | 0.6892    | 0.6299 | 0.5872 |
| 0.2815        | 0.0833 | 5000 | 1.7752          | 0.6423   | 0.6905    | 0.6423 | 0.6034 |
| 0.2525        | 0.0917 | 5500 | 1.6552          | 0.6450   | 0.6879    | 0.6450 | 0.6082 |
| 0.2271        | 0.1    | 6000 | 1.6523          | 0.6575   | 0.6916    | 0.6575 | 0.6278 |
| 0.3591        | 0.1083 | 6500 | 1.7169          | 0.6542   | 0.6985    | 0.6542 | 0.6238 |
| 0.2659        | 0.1167 | 7000 | 1.7209          | 0.6439   | 0.7090    | 0.6439 | 0.6180 |
| 0.2337        | 0.125  | 7500 | 1.7631          | 0.6531   | 0.7019    | 0.6531 | 0.6158 |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.9.0+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1