Downloads · 30 days
0
llama_7b_qlora_pds-eval-test
DevaMalla/llama_7b_qlora_pds-eval-test
llama_7b_qlora_pds-eval-test is a machine learning model from DevaMalla. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Sep 25, 2023
Repo size
269 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin134 MB · 100%
At a glance
- Access
- Public
- Created
- Sep 22, 2023
- Updated
- Sep 25, 2023
- SHA
- 8bb3e28a
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. -->
llama_7b_qlora_pds-eval-test
This model is a fine-tuned version of DevaMalla/llama7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0622
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: 40
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6779 | 0.09 | 5 | 1.5894 |
| 1.5194 | 0.19 | 10 | 1.4528 |
| 1.3984 | 0.28 | 15 | 1.3331 |
| 1.2809 | 0.37 | 20 | 1.2312 |
| 1.1953 | 0.46 | 25 | 1.1674 |
| 1.1197 | 0.56 | 30 | 1.1217 |
| 1.0967 | 0.65 | 35 | 1.0921 |
| 1.0739 | 0.74 | 40 | 1.0756 |
| 1.0613 | 0.83 | 45 | 1.0672 |
| 1.0578 | 0.93 | 50 | 1.0633 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3
- Created
- Sep 22, 2023
- Updated
- Sep 25, 2023