---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Finetuned_FLAN-T5_VALUE_finetuning_lr3e-4
  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. -->

# Finetuned_FLAN-T5_VALUE_finetuning_lr3e-4

This model is a fine-tuned version of [liuyanchen1015/FLAN-T5_GLUE_finetuning_lr3e-4](https://huggingface.co/liuyanchen1015/FLAN-T5_GLUE_finetuning_lr3e-4) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1268
- Accuracy: 0.8823

## 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: 0.0003
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.06          | 0.17  | 2500  | 0.0907          | 0.8692   |
| 0.0623        | 0.34  | 5000  | 0.0920          | 0.8698   |
| 0.0629        | 0.51  | 7500  | 0.0875          | 0.8701   |
| 0.0641        | 0.68  | 10000 | 0.0892          | 0.8709   |
| 0.0634        | 0.85  | 12500 | 0.0908          | 0.8696   |
| 0.0627        | 1.02  | 15000 | 0.0939          | 0.8723   |
| 0.0467        | 1.18  | 17500 | 0.0949          | 0.8738   |
| 0.0485        | 1.35  | 20000 | 0.0954          | 0.8731   |
| 0.0496        | 1.52  | 22500 | 0.0909          | 0.8729   |
| 0.0497        | 1.69  | 25000 | 0.0942          | 0.8765   |
| 0.0509        | 1.86  | 27500 | 0.0925          | 0.8753   |
| 0.047         | 2.03  | 30000 | 0.1024          | 0.8781   |
| 0.0346        | 2.2   | 32500 | 0.1011          | 0.8791   |
| 0.0364        | 2.37  | 35000 | 0.1013          | 0.8773   |
| 0.0359        | 2.54  | 37500 | 0.1013          | 0.8785   |
| 0.0374        | 2.71  | 40000 | 0.1002          | 0.8785   |
| 0.0367        | 2.88  | 42500 | 0.1015          | 0.8787   |
| 0.0338        | 3.05  | 45000 | 0.1199          | 0.8779   |
| 0.0253        | 3.22  | 47500 | 0.1191          | 0.8791   |
| 0.0256        | 3.38  | 50000 | 0.1165          | 0.8787   |
| 0.0257        | 3.55  | 52500 | 0.1136          | 0.88     |
| 0.0265        | 3.72  | 55000 | 0.1092          | 0.881    |
| 0.026         | 3.89  | 57500 | 0.1131          | 0.8814   |
| 0.0233        | 4.06  | 60000 | 0.1270          | 0.8798   |
| 0.018         | 4.23  | 62500 | 0.1291          | 0.8808   |
| 0.0191        | 4.4   | 65000 | 0.1269          | 0.8814   |
| 0.0191        | 4.57  | 67500 | 0.1279          | 0.8816   |
| 0.0186        | 4.74  | 70000 | 0.1264          | 0.8824   |
| 0.0184        | 4.91  | 72500 | 0.1268          | 0.8823   |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.0+cu117
- Datasets 2.10.1
- Tokenizers 0.12.1