zephyr-7b-gemma-sft-v0.1
HuggingFaceH4's 8.5B Zephyr chat model built on Gemma 7B via supervised fine-tuning on the Deita 10k dataset.
Base model
google/gemma-7b
Model Card
This model is a fine-tuned version of google/gemma-7b on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:
- Loss: 0.9732
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9482 | 1.0 | 299 | 0.9848 |
| 0.8139 | 2.0 | 599 | 0.9610 |
| 0.722 | 2.99 | 897 | 0.9732 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1
Author
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Author
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.