metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b
datasets:
- generator
model-index:
- name: gemma-2b-dolly-qa
results: []
gemma-2b-dolly-qa
This model is a fine-tuned version of google/gemma-2b on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.8003
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 1480
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3815 | 1.64 | 100 | 2.0042 |
| 1.934 | 3.28 | 200 | 2.0421 |
| 1.7512 | 4.92 | 300 | 2.1031 |
| 1.5047 | 6.56 | 400 | 2.3441 |
| 1.276 | 8.2 | 500 | 2.6745 |
| 1.0163 | 9.84 | 600 | 2.9221 |
| 0.7745 | 11.48 | 700 | 3.3954 |
| 0.5846 | 13.11 | 800 | 4.0620 |
| 0.4107 | 14.75 | 900 | 4.2286 |
| 0.2873 | 16.39 | 1000 | 4.6660 |
| 0.2062 | 18.03 | 1100 | 5.0101 |
| 0.1397 | 19.67 | 1200 | 5.3291 |
| 0.1046 | 21.31 | 1300 | 5.6700 |
| 0.0788 | 22.95 | 1400 | 5.8003 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0a0+cxx11.abi
- Datasets 2.18.0
- Tokenizers 0.15.2