metadata
base_model: google/gemma-7b
library_name: peft
license: gemma
tags:
- generated_from_trainer
model-index:
- name: gemma-7b_oasst1_l0.0002_32-8-8-8-8
results: []
gemma-7b_oasst1_l0.0002_32-8-8-8-8
This model is a fine-tuned version of google/gemma-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1333
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: 1
- seed: 0
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 1875
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7307 | 0.0018 | 1 | 1.9676 |
| 1.9449 | 0.3392 | 187 | 1.6057 |
| 1.3608 | 0.6783 | 374 | 1.6356 |
| 1.3231 | 1.0175 | 561 | 1.6897 |
| 1.2619 | 1.3566 | 748 | 1.8127 |
| 1.0971 | 1.6958 | 935 | 1.7752 |
| 0.5605 | 2.0349 | 1122 | 1.9491 |
| 0.9008 | 2.3741 | 1309 | 1.8904 |
| 0.9005 | 2.7132 | 1496 | 2.0851 |
| 0.6184 | 3.0524 | 1683 | 2.1799 |
| 0.5547 | 3.3915 | 1870 | 2.1523 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1