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-gemini1_5flash-32k
results: []
gemma2b-summarize-gemini1_5flash-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: 2.6817
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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 128
- 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 |
|---|---|---|---|
| 2.0459 | 1.0 | 26 | 2.8633 |
| 1.2724 | 2.0 | 52 | 2.7063 |
| 1.1654 | 3.0 | 78 | 2.6695 |
| 1.1056 | 4.0 | 104 | 2.6545 |
| 1.0615 | 5.0 | 130 | 2.6669 |
| 1.0347 | 6.0 | 156 | 2.6682 |
| 1.0216 | 7.0 | 182 | 2.6747 |
| 1.0204 | 8.0 | 208 | 2.6796 |
| 1.0071 | 9.0 | 234 | 2.6812 |
| 1.0088 | 10.0 | 260 | 2.6817 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1