metadata
license: gemma
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
- ipex
- GPU Max 1100
base_model: google/gemma-2b
datasets:
- generator
model-index:
- name: gemma-Chimdi-LORA-TUNED
results: []
gemma-Chimdi-LORA-TUNED
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: 2.1484
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training Hardware
This model was trained using 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 |
|---|---|---|---|
| 2.8528 | 0.8197 | 100 | 2.5372 |
| 2.4491 | 1.6393 | 200 | 2.3103 |
| 2.2851 | 2.4590 | 300 | 2.2148 |
| 2.2162 | 3.2787 | 400 | 2.1720 |
| 2.1935 | 4.0984 | 500 | 2.1484 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.0.post0+cxx11.abi
- Datasets 2.19.0
- Tokenizers 0.19.1