metadata
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: google/gemma-2b-it
model-index:
- name: shawgpt-ft
results: []
shawgpt-ft
This model is a fine-tuned version of google/gemma-2b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.8439
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.9288 | 0.8 | 1 | 5.5505 |
| 6.9042 | 1.6 | 2 | 5.4949 |
| 6.7836 | 2.4 | 3 | 5.3725 |
| 3.2963 | 4.0 | 5 | 5.1469 |
| 6.4036 | 4.8 | 6 | 5.0534 |
| 6.2748 | 5.6 | 7 | 4.9738 |
| 6.1622 | 6.4 | 8 | 4.9099 |
| 3.0478 | 8.0 | 10 | 4.8439 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2