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-256k
results: []
gemma7b-summarize-gpt4o-256k
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: 2.4681
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 |
|---|---|---|---|
| 1.0805 | 1.0 | 439 | 2.5210 |
| 0.9397 | 2.0 | 878 | 2.4361 |
| 0.8628 | 3.0 | 1317 | 2.4056 |
| 0.8131 | 4.0 | 1756 | 2.4177 |
| 0.7788 | 5.0 | 2195 | 2.4166 |
| 0.771 | 6.0 | 2634 | 2.4329 |
| 0.7459 | 7.0 | 3073 | 2.4458 |
| 0.745 | 8.0 | 3512 | 2.4609 |
| 0.7433 | 9.0 | 3951 | 2.4640 |
| 0.7376 | 10.0 | 4390 | 2.4681 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1