metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google/madlad400-3b-mt
datasets:
- generator
metrics:
- bleu
model-index:
- name: traduction_fon_french
results: []
traduction_fon_french
This model is a fine-tuned version of google/madlad400-3b-mt on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.2051
- Bleu: 4.2618
- Gen Len: 7.1747
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: 0.00016
- train_batch_size: 18
- eval_batch_size: 18
- 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 | Gen Len |
|---|---|---|---|---|---|
| 1.8931 | 1.0 | 4957 | 4.2563 | 4.206 | 7.2216 |
| 1.8748 | 2.0 | 9914 | 4.2353 | 4.3796 | 7.1632 |
| 1.9018 | 3.0 | 14871 | 4.2051 | 4.2618 | 7.1747 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1