metadata
license: mit
base_model: VietAI/envit5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: envit5-base
results: []
envit5-base
This model is a fine-tuned version of VietAI/envit5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3981
- Bleu: 1.1676
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| No log | 1.0 | 4 | 3.6615 | 0.7586 |
| No log | 2.0 | 8 | 3.4541 | 1.2385 |
| No log | 3.0 | 12 | 3.3981 | 1.1676 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1