metadata
tags:
- generated_from_trainer
model-index:
- name: spark-name-ja-to-en
results: []
spark-name-ja-to-en
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5313
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 1 | 5.2178 |
| No log | 2.0 | 2 | 4.7373 |
| No log | 3.0 | 3 | 4.5313 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.0.1+cpu
- Datasets 2.19.1
- Tokenizers 0.19.1