metadata
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b
datasets:
- llama-duo/synth_summarize_dataset_dedup
model-index:
- name: gemma2b-summarize-claude3sonnet-32k
results: []
gemma2b-summarize-claude3sonnet-32k
This model is a fine-tuned version of google/gemma-2b on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:
- Loss: 2.5627
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- total_eval_batch_size: 24
- 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 |
|---|---|---|---|
| 1.187 | 0.9951 | 101 | 2.4971 |
| 1.0678 | 2.0 | 203 | 2.4806 |
| 1.0113 | 2.9951 | 304 | 2.4777 |
| 0.9692 | 4.0 | 406 | 2.5005 |
| 0.9448 | 4.9951 | 507 | 2.5205 |
| 0.906 | 6.0 | 609 | 2.5325 |
| 0.8867 | 6.9951 | 710 | 2.5459 |
| 0.8783 | 8.0 | 812 | 2.5595 |
| 0.8501 | 8.9951 | 913 | 2.5624 |
| 0.8569 | 9.9507 | 1010 | 2.5627 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1