gemma-7b-sft-full-longest-1k-v1
This model is a fine-tuned version of google/gemma-7b on the HuggingFaceH4/OpenHermes-2.5-1k-longest dataset. It achieves the following results on the evaluation set:
- Loss: 1.0137
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: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- 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
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9689 | 5.0 | 30 | 1.4644 |
| 1.1624 | 10.0 | 60 | 1.0363 |
| 1.0662 | 15.0 | 90 | 1.0137 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.