metadata
library_name: transformers
license: mit
base_model: facebook/m2m100_418M
tags:
- generated_from_trainer
model-index:
- name: m2m-amharic-antonym2
results: []
m2m-amharic-antonym2
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: 0.4000
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.3254 | 1.0 | 60 | 5.0654 |
| 3.2923 | 2.0 | 120 | 3.0617 |
| 1.4883 | 3.0 | 180 | 1.3369 |
| 0.5846 | 4.0 | 240 | 0.5542 |
| 0.4111 | 5.0 | 300 | 0.4232 |
| 0.3265 | 6.0 | 360 | 0.4001 |
| 0.288 | 7.0 | 420 | 0.3914 |
| 0.2587 | 8.0 | 480 | 0.3890 |
| 0.2228 | 9.0 | 540 | 0.3940 |
| 0.2177 | 10.0 | 600 | 0.4000 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1