metadata
base_model: google/mt5-base
tags:
- generated_from_trainer
model-index:
- name: output
results: []
language:
- fa
datasets:
- SeyedAli/Persian-Text-Paraphrasing
Persian-Text-paraphraser-mT5
This model is a fine-tuned version of google/mt5-base on SeyedAli/Persian-Text-Paraphrasing dataset. It achieves the following results on the evaluation set:
- Loss: 0.2334
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: 2e-05
- train_batch_size: 5
- eval_batch_size: 5
- 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 |
|---|---|---|---|
| No log | 1.0 | 160 | 0.4026 |
| No log | 2.0 | 320 | 0.2853 |
| No log | 3.0 | 480 | 0.2543 |
| 1.5981 | 4.0 | 640 | 0.2466 |
| 1.5981 | 5.0 | 800 | 0.2408 |
| 1.5981 | 6.0 | 960 | 0.2367 |
| 0.3535 | 7.0 | 1120 | 0.2363 |
| 0.3535 | 8.0 | 1280 | 0.2344 |
| 0.3535 | 9.0 | 1440 | 0.2334 |
| 0.3151 | 10.0 | 1600 | 0.2334 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3