metadata
license: gemma
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
- ipex
- Intel(R) Data Center GPU Max 1100
- GPU Max 1100
datasets:
- generator
base_model: google/gemma-2b
model-index:
- name: gemma-2b-dolly-ds-lora
results: []
gemma-2b-dolly-ds-lora
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: 2.1563
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training Hardware
Intel(R) Data Center GPU Max 1100
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 593
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8468 | 0.82 | 100 | 2.5258 |
| 2.4514 | 1.64 | 200 | 2.3193 |
| 2.3108 | 2.46 | 300 | 2.2252 |
| 2.2184 | 3.28 | 400 | 2.1790 |
| 2.1956 | 4.1 | 500 | 2.1563 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.0.1a0+cxx11.abi
- Datasets 2.18.0
- Tokenizers 0.15.2