Downloads · 30 days
0
stg-cli13b-t6.mt.him.cln.inter-b4s1e1-20231212-0801
G-ML-Hyly/stg-cli13b-t6.mt.him.cln.inter-b4s1e1-20231212-0801
stg-cli13b-t6.mt.him.cln.inter-b4s1e1-20231212-0801 is a machine learning model from G-ML-Hyly. 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 llama2.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Dec 12, 2023
Repo size
752 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors125 MB · 98%
At a glance
- License
- llama2
- Access
- Public
- Created
- Dec 12, 2023
- Updated
- Dec 12, 2023
- SHA
- c792d088
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. -->
stg-cli13b-t6.mt.him.cln.inter-b4s1e1-20231212-0801
This model is a fine-tuned version of codellama/CodeLlama-13b-Instruct-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0546
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.367 | 0.03 | 100 | 0.0896 |
| 0.0809 | 0.07 | 200 | 0.0730 |
| 0.0721 | 0.1 | 300 | 0.0687 |
| 0.065 | 0.13 | 400 | 0.0632 |
| 0.0629 | 0.17 | 500 | 0.0636 |
| 0.0618 | 0.2 | 600 | 0.0608 |
| 0.0606 | 0.23 | 700 | 0.0615 |
| 0.0604 | 0.27 | 800 | 0.0599 |
| 0.0598 | 0.3 | 900 | 0.0601 |
| 0.0599 | 0.33 | 1000 | 0.0598 |
| 0.0613 | 0.37 | 1100 | 0.0598 |
| 0.0597 | 0.4 | 1200 | 0.0590 |
| 0.06 | 0.43 | 1300 | 0.0589 |
| 0.058 | 0.47 | 1400 | 0.0589 |
| 0.058 | 0.5 | 1500 | 0.0575 |
| 0.0578 | 0.53 | 1600 | 0.0576 |
| 0.0569 | 0.57 | 1700 | 0.0566 |
| 0.0573 | 0.6 | 1800 | 0.0574 |
| 0.0577 | 0.63 | 1900 | 0.0567 |
| 0.0574 | 0.67 | 2000 | 0.0561 |
| 0.0566 | 0.7 | 2100 | 0.0559 |
| 0.056 | 0.74 | 2200 | 0.0562 |
| 0.0563 | 0.77 | 2300 | 0.0556 |
| 0.0551 | 0.8 | 2400 | 0.0553 |
| 0.0554 | 0.84 | 2500 | 0.0551 |
| 0.0553 | 0.87 | 2600 | 0.0550 |
| 0.0548 | 0.9 | 2700 | 0.0547 |
| 0.0547 | 0.94 | 2800 | 0.0546 |
| 0.0547 | 0.97 | 2900 | 0.0546 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- License
- llama2
- Created
- Dec 12, 2023
- Updated
- Dec 12, 2023