metadata
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- llama-duo/synth_summarize_dataset_dedup
base_model: google/gemma-7b
model-index:
- name: gemma7b-summarize-gpt4o-64k
results: []
gemma7b-summarize-gpt4o-64k
This model is a fine-tuned version of google/gemma-7b on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:
- Loss: 2.5157
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: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 16
- 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 |
|---|---|---|---|
| 1.3554 | 0.9954 | 109 | 2.6451 |
| 1.0898 | 2.0 | 219 | 2.5083 |
| 1.0434 | 2.9954 | 328 | 2.4801 |
| 0.9864 | 4.0 | 438 | 2.4743 |
| 0.9371 | 4.9954 | 547 | 2.4854 |
| 0.9157 | 6.0 | 657 | 2.4642 |
| 0.8657 | 6.9954 | 766 | 2.5076 |
| 0.8393 | 8.0 | 876 | 2.5159 |
| 0.8462 | 8.9954 | 985 | 2.5185 |
| 0.8359 | 9.9543 | 1090 | 2.5157 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1