Downloads · 30 days
0
mistral_instruct_classify30k-1
greatakela/mistral_instruct_classify30k-1
mistral_instruct_classify30k-1 is a machine learning model from greatakela. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Dec 4, 2023
Repo size
218 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors218 MB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 4, 2023
- Updated
- Dec 4, 2023
- SHA
- c1499d2f
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_instruct_classify30k-1
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3976
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: 6
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5706 | 0.04 | 168 | 0.5734 |
| 0.4594 | 1.04 | 336 | 0.4755 |
| 0.3872 | 2.04 | 504 | 0.4252 |
| 0.3228 | 3.04 | 672 | 0.4019 |
| 0.2801 | 4.04 | 840 | 0.3976 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- License
- apache-2.0
- Created
- Dec 4, 2023
- Updated
- Dec 4, 2023