metadata
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
datasets:
- chansung/merged_ds_coding
model-index:
- name: coding_llamaduo_result3
results: []
coding_llamaduo_result3
This model is a fine-tuned version of google/gemma-7b on the chansung/merged_ds_coding dataset. It achieves the following results on the evaluation set:
- Loss: 1.2481
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: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7425 | 1.0 | 164 | 1.1824 |
0.6196 | 2.0 | 328 | 1.1435 |
0.5124 | 3.0 | 492 | 1.1461 |
0.4403 | 4.0 | 656 | 1.2068 |
0.4072 | 5.0 | 820 | 1.2481 |
Framework versions
- PEFT 0.7.1
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1