Downloads · 30 days
1
5% of all-time downloads
zephyr-7b-gemma-sft-10p
QinLiuNLP/zephyr-7b-gemma-sft-10p
zephyr-7b-gemma-sft-10p is a machine learning model from QinLiuNLP. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
19
Public
Repo size
55.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors37.6 MB · 68%
At a glance
- Library
- peft
- License
- gemma
- Model type
- gemma
- Access
- Public
- Created
- Apr 21, 2024
- Updated
- Apr 21, 2024
- SHA
- b48fa9fe
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
zephyr-7b-gemma-sft-10p
This model is a fine-tuned version of google/gemma-7b on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 1.1202
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- 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 |
|---|---|---|---|
| 0.9388 | 1.0 | 328 | 1.1538 |
| 0.9232 | 2.0 | 656 | 1.1174 |
| 0.8492 | 3.0 | 984 | 1.1202 |
Framework versions
- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2
- Library
- peft
- Type
- gemma
- License
- gemma
- Created
- Apr 21, 2024
- Updated
- Apr 21, 2024