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-256k
results: []
gemma7b-summarize-claude3sonnet-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: 2.4860
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 |
|---|---|---|---|
| 0.964 | 0.9992 | 606 | 2.4850 |
| 0.8499 | 2.0 | 1213 | 2.4393 |
| 0.7939 | 2.9992 | 1819 | 2.4242 |
| 0.7465 | 4.0 | 2426 | 2.4363 |
| 0.7312 | 4.9992 | 3032 | 2.4391 |
| 0.7253 | 6.0 | 3639 | 2.4593 |
| 0.7042 | 6.9992 | 4245 | 2.4711 |
| 0.6928 | 8.0 | 4852 | 2.4713 |
| 0.6924 | 8.9992 | 5458 | 2.4815 |
| 0.6936 | 9.9918 | 6060 | 2.4860 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1