metadata
license: mit
base_model: facebook/m2m100_418M
tags:
- generated_from_trainer
model-index:
- name: output
results: []
output
This model is a fine-tuned version of facebook/m2m100_418M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6394
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.7525 | 0.53 | 100 | 0.9179 |
0.7831 | 1.06 | 200 | 0.6902 |
0.6143 | 1.6 | 300 | 0.6662 |
0.5988 | 2.13 | 400 | 0.6493 |
0.5075 | 2.66 | 500 | 0.6415 |
0.4766 | 3.19 | 600 | 0.6408 |
0.4445 | 3.72 | 700 | 0.6394 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2