metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: VietAI/vit5-base
metrics:
- rouge
model-index:
- name: TaiDepZai999-UIT-Vit5
results: []
TaiDepZai999-UIT-Vit5
This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 26.7447
- Rouge1: 10.0592
- Rouge2: 4.8665
- Rougel: 8.6097
- Rougelsum: 8.6121
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 221
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 0.9968 | 78 | 29.6912 | 10.6188 | 5.0941 | 9.0232 | 9.0244 |
| No log | 1.9936 | 156 | 28.8059 | 10.5140 | 5.0396 | 8.9231 | 8.9360 |
| No log | 2.9904 | 234 | 26.7447 | 10.0592 | 4.8665 | 8.6097 | 8.6121 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1