metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mt5-small-Corrupted-Zarma12
results: []
mt5-small-Corrupted-Zarma12
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0345
- Bleu: 20.2823
- Gen Len: 18.2409
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|
| 0.0985 | 1.0 | 5951 | 0.0574 | 19.9606 | 18.2422 |
| 0.0632 | 2.0 | 11902 | 0.0390 | 20.2407 | 18.24 |
| 0.0507 | 3.0 | 17853 | 0.0345 | 20.2823 | 18.2409 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1