metadata
library_name: transformers
license: mit
base_model: facebook/m2m100_418M
tags:
- translation
- generated_from_trainer
model-index:
- name: m2m100_418M-hi-en_new
results: []
m2m100_418M-hi-en_new
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: 0.8994
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0884 | 1.0 | 5215 | 1.0170 |
| 0.8419 | 2.0 | 10430 | 0.9381 |
| 0.6706 | 3.0 | 15645 | 0.9036 |
| 0.5366 | 4.0 | 20860 | 0.9006 |
| 0.4602 | 5.0 | 26075 | 0.8994 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1