Downloads · 30 days
0
mistral-GPT-finetune
Sneka/mistral-GPT-finetune
mistral-GPT-finetune is a machine learning model from Sneka. 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 2, 2023
Repo size
610 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors609 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 2, 2023
- Updated
- Dec 2, 2023
- SHA
- 595ca193
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-GPT-finetune
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: 0.3634
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 18
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7398 | 0.57 | 50 | 0.9383 |
| 0.5873 | 1.14 | 100 | 0.5379 |
| 0.3598 | 1.71 | 150 | 0.4180 |
| 0.263 | 2.29 | 200 | 0.3726 |
| 0.1668 | 2.86 | 250 | 0.3334 |
| 0.126 | 3.43 | 300 | 0.3242 |
| 0.1027 | 4.0 | 350 | 0.3099 |
| 0.0763 | 4.57 | 400 | 0.3186 |
| 0.0597 | 5.14 | 450 | 0.3405 |
| 0.0555 | 5.71 | 500 | 0.3347 |
| 0.0499 | 6.29 | 550 | 0.3444 |
| 0.0407 | 6.86 | 600 | 0.3323 |
| 0.0354 | 7.43 | 650 | 0.3456 |
| 0.0395 | 8.0 | 700 | 0.3469 |
| 0.0309 | 8.57 | 750 | 0.3722 |
| 0.0308 | 9.14 | 800 | 0.3894 |
| 0.0279 | 9.71 | 850 | 0.3817 |
| 0.0311 | 10.29 | 900 | 0.3765 |
| 0.0275 | 10.86 | 950 | 0.3646 |
| 0.0267 | 11.43 | 1000 | 0.3634 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- License
- apache-2.0
- Created
- Dec 2, 2023
- Updated
- Dec 2, 2023