Downloads · 30 days
17
17% of all-time downloads
Mistral-7B-v0.1-oasst-top1
andreaschandra/Mistral-7B-v0.1-oasst-top1
Mistral-7B-v0.1-oasst-top1 is a machine learning model from andreaschandra. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
100
Public
Repo size
1.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jan 7, 2024
- Updated
- Jan 7, 2024
- SHA
- 51fb5e0f
Base models
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. -->
Mistral-7B-v0.1-oasst-top1
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8934
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8235 | 1.0 | 50 | 2.2676 |
| 1.2795 | 2.0 | 100 | 2.4106 |
| 0.9641 | 3.0 | 150 | 2.7605 |
| 0.4394 | 4.0 | 200 | 2.8580 |
| 0.4801 | 5.0 | 250 | 2.8934 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Library
- peft
- License
- apache-2.0
- Created
- Jan 7, 2024
- Updated
- Jan 7, 2024