metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b
model-index:
- name: gemma-2b-spanishbillionwords
results: []
gemma-2b-spanishbillionwords
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0578
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2899 | 1.0 | 1 | 4.1511 |
| 1.2899 | 2.0 | 2 | 4.1451 |
| 1.2466 | 3.0 | 3 | 4.1311 |
| 1.1503 | 4.0 | 4 | 4.1179 |
| 1.0691 | 5.0 | 5 | 4.1011 |
| 0.9985 | 6.0 | 6 | 4.0873 |
| 0.9366 | 7.0 | 7 | 4.0770 |
| 0.8845 | 8.0 | 8 | 4.0662 |
| 0.8436 | 9.0 | 9 | 4.0618 |
| 0.8154 | 10.0 | 10 | 4.0578 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0
- Pytorch 2.2.1+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2