metadata
license: mit
base_model: facebook/m2m100_418M
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: TL_T
results: []
TL_T
This model is a fine-tuned version of facebook/m2m100_418M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0123
- Bleu: 23.2241
- Gen Len: 36.8799
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: 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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 496 | 1.1522 | 19.1623 | 36.631 |
| 2.2335 | 2.0 | 992 | 1.0123 | 23.2241 | 36.8799 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1