---
library_name: transformers
license: apache-2.0
base_model: google/flan-t5-large
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: flanT5_large_FINAL_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. -->

# flanT5_large_FINAL_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: 2.2262
- Accuracy: 0.7917
- Precision: 0.7946
- Recall: 0.7867
- F1 score: 0.7906

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | Precision | Recall | F1 score |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|
| 1.2184        | 0.3910 | 2500  | 0.9222          | 0.7383   | 0.8824    | 0.55   | 0.6776   |
| 1.2323        | 0.7820 | 5000  | 1.6840          | 0.6617   | 0.6222    | 0.8233 | 0.7088   |
| 1.0084        | 1.1730 | 7500  | 0.9030          | 0.7583   | 0.7969    | 0.6933 | 0.7415   |
| 0.9192        | 1.5640 | 10000 | 1.3138          | 0.6917   | 0.6322    | 0.9167 | 0.7483   |
| 0.8932        | 1.9550 | 12500 | 1.0240          | 0.7467   | 0.6927    | 0.8867 | 0.7778   |
| 0.7463        | 2.3459 | 15000 | 0.9096          | 0.765    | 0.7870    | 0.7267 | 0.7556   |
| 0.7129        | 2.7369 | 17500 | 0.9885          | 0.765    | 0.8046    | 0.7    | 0.7487   |
| 0.6329        | 3.1279 | 20000 | 1.1713          | 0.78     | 0.78      | 0.78   | 0.78     |
| 0.5556        | 3.5189 | 22500 | 1.1964          | 0.7783   | 0.7313    | 0.88   | 0.7988   |
| 0.4961        | 3.9099 | 25000 | 1.0480          | 0.7783   | 0.8081    | 0.73   | 0.7671   |
| 0.3171        | 4.3009 | 27500 | 1.4131          | 0.785    | 0.8178    | 0.7333 | 0.7733   |
| 0.2846        | 4.6919 | 30000 | 1.4925          | 0.755    | 0.7429    | 0.78   | 0.7610   |
| 0.2499        | 5.0829 | 32500 | 1.6449          | 0.77     | 0.7396    | 0.8333 | 0.7837   |
| 0.159         | 5.4739 | 35000 | 1.5721          | 0.7917   | 0.8136    | 0.7567 | 0.7841   |
| 0.1929        | 5.8649 | 37500 | 1.7558          | 0.7667   | 0.7721    | 0.7567 | 0.7643   |
| 0.1236        | 6.2559 | 40000 | 1.9731          | 0.775    | 0.7778    | 0.77   | 0.7739   |
| 0.0855        | 6.6469 | 42500 | 2.0351          | 0.755    | 0.7179    | 0.84   | 0.7742   |
| 0.0952        | 7.0378 | 45000 | 1.8523          | 0.7833   | 0.7724    | 0.8033 | 0.7876   |
| 0.0646        | 7.4288 | 47500 | 1.8575          | 0.775    | 0.7603    | 0.8033 | 0.7812   |
| 0.0562        | 7.8198 | 50000 | 1.9564          | 0.7783   | 0.7685    | 0.7967 | 0.7823   |
| 0.0324        | 8.2108 | 52500 | 2.1755          | 0.7767   | 0.7823    | 0.7667 | 0.7744   |
| 0.0467        | 8.6018 | 55000 | 2.0450          | 0.7733   | 0.8015    | 0.7267 | 0.7622   |
| 0.0419        | 8.9928 | 57500 | 1.9761          | 0.7917   | 0.7760    | 0.82   | 0.7974   |
| 0.0222        | 9.3838 | 60000 | 2.2657          | 0.79     | 0.7806    | 0.8067 | 0.7934   |
| 0.0303        | 9.7748 | 62500 | 2.2262          | 0.7917   | 0.7946    | 0.7867 | 0.7906   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1