Downloads · 30 days
3
23% of all-time downloads
shawgpt-ft
andrewverse/shawgpt-ft
shawgpt-ft is a machine learning model from andrewverse. 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
13
Public
Repo size
8.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.4 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Mar 13, 2024
- Updated
- Mar 13, 2024
- SHA
- e95f4a75
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: 1.8954
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: 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5947 | 0.92 | 3 | 3.9670 |
| 4.057 | 1.85 | 6 | 3.4492 |
| 3.4868 | 2.77 | 9 | 2.9974 |
| 2.2798 | 4.0 | 13 | 2.5878 |
| 2.7141 | 4.92 | 16 | 2.3461 |
| 2.4038 | 5.85 | 19 | 2.1695 |
| 2.1894 | 6.77 | 22 | 2.0207 |
| 1.539 | 8.0 | 26 | 1.9470 |
| 2.006 | 8.92 | 29 | 1.9074 |
| 1.3911 | 9.23 | 30 | 1.8954 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- peft
- License
- apache-2.0
- Created
- Mar 13, 2024
- Updated
- Mar 13, 2024