metadata
license: other
base_model: laurentiubp/CataLLaMA-v0.1.2
tags:
- generated_from_trainer
model-index:
- name: CataLLaMA-v0.2.0
results: []
CataLLaMA-v0.2.0
This model is a fine-tuned version of laurentiubp/CataLLaMA-v0.1.2 on the Catalan-Instruct dataset. It achieves the following results on the evaluation set:
- Loss: 0.8528
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: 1e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- total_train_batch_size: 60
- total_eval_batch_size: 60
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8002 | 0.22 | 200 | 0.8989 |
| 0.8068 | 0.43 | 400 | 0.8835 |
| 0.7722 | 0.65 | 600 | 0.8654 |
| 0.7805 | 0.86 | 800 | 0.8528 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.2