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-4k
results: []
gemma2b-summarize-claude3sonnet-4k
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: 2.5362
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 |
|---|---|---|---|
| 2.6184 | 1.0 | 13 | 2.7931 |
| 1.8166 | 2.0 | 26 | 2.5963 |
| 1.5365 | 3.0 | 39 | 2.5611 |
| 1.3191 | 4.0 | 52 | 2.5480 |
| 1.2353 | 5.0 | 65 | 2.5346 |
| 1.1927 | 6.0 | 78 | 2.5317 |
| 1.1527 | 7.0 | 91 | 2.5331 |
| 1.1355 | 8.0 | 104 | 2.5356 |
| 1.1336 | 9.0 | 117 | 2.5359 |
| 1.1358 | 10.0 | 130 | 2.5362 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1