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-claude3sonnet-128k
results: []
gemma7b-summarize-claude3sonnet-128k
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: 2.5222
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 |
|---|---|---|---|
| 1.0247 | 0.9983 | 301 | 2.5396 |
| 0.9144 | 2.0 | 603 | 2.4619 |
| 0.8616 | 2.9983 | 904 | 2.4534 |
| 0.8075 | 4.0 | 1206 | 2.4530 |
| 0.7724 | 4.9983 | 1507 | 2.4674 |
| 0.7571 | 6.0 | 1809 | 2.4825 |
| 0.7389 | 6.9983 | 2110 | 2.5147 |
| 0.7223 | 8.0 | 2412 | 2.5135 |
| 0.7178 | 8.9983 | 2713 | 2.5209 |
| 0.7148 | 9.9834 | 3010 | 2.5222 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1