metadata
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
datasets:
- llama-duo/synth_summarize_dataset
model-index:
- name: gemma7b-summarize-gemini1.5flash-30k
results: []
gemma7b-summarize-gemini1.5flash-30k
This model is a fine-tuned version of google/gemma-7b on the llama-duo/synth_summarize_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 3.3804
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: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0256 | 1.0 | 110 | 2.3887 |
| 0.8325 | 2.0 | 220 | 2.2270 |
| 0.749 | 3.0 | 330 | 2.2333 |
| 0.6755 | 4.0 | 440 | 2.2993 |
| 0.6197 | 5.0 | 550 | 2.3820 |
| 0.5208 | 6.0 | 660 | 2.5869 |
| 0.4474 | 7.0 | 770 | 2.8389 |
| 0.4044 | 8.0 | 880 | 3.1029 |
| 0.3573 | 9.0 | 990 | 3.3573 |
| 0.354 | 10.0 | 1100 | 3.3804 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1