Downloads · 30 days
7
58% of all-time downloads
shawgpt-ft
TheHiddenCake/shawgpt-ft
shawgpt-ft is a machine learning model from TheHiddenCake. 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
12
Public
Repo size
86.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors33.6 MB · 99%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Oct 5, 2024
- Updated
- Oct 18, 2024
- SHA
- 9fb65c3d
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. -->
shawgpt-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3580
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: 0.00015
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6061 | 0.9231 | 3 | 4.0341 |
| 4.1745 | 1.8462 | 6 | 3.6105 |
| 3.6789 | 2.7692 | 9 | 3.2032 |
| 2.4218 | 4.0 | 13 | 2.7407 |
| 2.8571 | 4.9231 | 16 | 2.4606 |
| 2.4882 | 5.8462 | 19 | 2.2020 |
| 2.1619 | 6.7692 | 22 | 1.9563 |
| 1.4308 | 8.0 | 26 | 1.7393 |
| 1.732 | 8.9231 | 29 | 1.6256 |
| 1.571 | 9.8462 | 32 | 1.5250 |
| 1.4852 | 10.7692 | 35 | 1.4513 |
| 1.0409 | 12.0 | 39 | 1.4110 |
| 1.3861 | 12.9231 | 42 | 1.3930 |
| 1.3416 | 13.8462 | 45 | 1.3801 |
| 1.3437 | 14.7692 | 48 | 1.3716 |
| 1.0055 | 16.0 | 52 | 1.3639 |
| 1.3137 | 16.9231 | 55 | 1.3604 |
| 1.2979 | 17.8462 | 58 | 1.3585 |
| 0.9156 | 18.4615 | 60 | 1.3580 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Library
- peft
- License
- apache-2.0
- Created
- Oct 5, 2024
- Updated
- Oct 18, 2024