---
library_name: transformers
license: apache-2.0
base_model: google/flan-t5-large
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: flan_T5_MT
  results: []
---

<!-- 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. -->

# flan_T5_MT

This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8295
- Accuracy: 0.7971
- Precision: 0.7988
- Recall: 0.7941
- F1 score: 0.7965

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | Precision | Recall | F1 score |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|
| 1.1041        | 0.2103 | 2500  | 0.9414          | 0.7371   | 0.7346    | 0.7424 | 0.7384   |
| 0.8837        | 0.4205 | 5000  | 1.1617          | 0.7524   | 0.8994    | 0.5682 | 0.6965   |
| 0.8923        | 0.6308 | 7500  | 0.9163          | 0.7871   | 0.8306    | 0.7212 | 0.7720   |
| 0.8658        | 0.8410 | 10000 | 1.0822          | 0.7947   | 0.8711    | 0.6918 | 0.7711   |
| 0.7201        | 1.0513 | 12500 | 1.0379          | 0.7794   | 0.7838    | 0.7718 | 0.7777   |
| 0.5277        | 1.2616 | 15000 | 1.1824          | 0.7994   | 0.8353    | 0.7459 | 0.7881   |
| 0.5173        | 1.4718 | 17500 | 1.0692          | 0.7806   | 0.7630    | 0.8141 | 0.7877   |
| 0.45          | 1.6821 | 20000 | 0.9608          | 0.7906   | 0.7913    | 0.7894 | 0.7903   |
| 0.3901        | 1.8923 | 22500 | 1.2113          | 0.7994   | 0.8041    | 0.7918 | 0.7979   |
| 0.2902        | 2.1026 | 25000 | 1.2724          | 0.7912   | 0.8098    | 0.7612 | 0.7847   |
| 0.1808        | 2.3129 | 27500 | 1.4793          | 0.7994   | 0.7956    | 0.8059 | 0.8007   |
| 0.1787        | 2.5231 | 30000 | 1.3220          | 0.8053   | 0.8100    | 0.7976 | 0.8038   |
| 0.1908        | 2.7334 | 32500 | 1.3844          | 0.8012   | 0.82      | 0.7718 | 0.7952   |
| 0.1709        | 2.9437 | 35000 | 1.6708          | 0.7924   | 0.7860    | 0.8035 | 0.7946   |
| 0.1183        | 3.1539 | 37500 | 1.5582          | 0.7912   | 0.7809    | 0.8094 | 0.7949   |
| 0.088         | 3.3642 | 40000 | 1.6673          | 0.8059   | 0.8342    | 0.7635 | 0.7973   |
| 0.0948        | 3.5744 | 42500 | 1.4679          | 0.8065   | 0.8318    | 0.7682 | 0.7988   |
| 0.0863        | 3.7847 | 45000 | 1.5944          | 0.7935   | 0.7939    | 0.7929 | 0.7934   |
| 0.0576        | 3.9950 | 47500 | 1.9939          | 0.7971   | 0.8046    | 0.7847 | 0.7945   |
| 0.0454        | 4.2052 | 50000 | 1.9647          | 0.7924   | 0.784     | 0.8071 | 0.7954   |
| 0.0407        | 4.4155 | 52500 | 1.9074          | 0.7959   | 0.7955    | 0.7965 | 0.7960   |
| 0.0404        | 4.6257 | 55000 | 1.9506          | 0.8076   | 0.8257    | 0.78   | 0.8022   |
| 0.0494        | 4.8360 | 57500 | 1.8295          | 0.7971   | 0.7988    | 0.7941 | 0.7965   |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0