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-gpt4o-8k
results: []
gemma2b-summarize-gpt4o-8k
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: 2.5343
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 |
|---|---|---|---|
| 2.5077 | 0.9730 | 18 | 2.7787 |
| 1.6701 | 2.0 | 37 | 2.6000 |
| 1.3757 | 2.9730 | 55 | 2.5216 |
| 1.2905 | 4.0 | 74 | 2.5137 |
| 1.2291 | 4.9730 | 92 | 2.5113 |
| 1.1946 | 6.0 | 111 | 2.5235 |
| 1.1618 | 6.9730 | 129 | 2.5300 |
| 1.1521 | 8.0 | 148 | 2.5335 |
| 1.147 | 8.9730 | 166 | 2.5343 |
| 1.14 | 9.7297 | 180 | 2.5343 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1