Downloads · 30 days
0
falcon-7b-instruct-FT-LoRA-8bit-test1
DanielSc4/falcon-7b-instruct-FT-LoRA-8bit-test1
falcon-7b-instruct-FT-LoRA-8bit-test1 is a machine learning model from DanielSc4. 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 Jun 27, 2023
Repo size
261 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin261 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 26, 2023
- Updated
- Jun 27, 2023
- SHA
- 804a78fd
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. -->
falcon-7b-instruct-FT-LoRA-8bit-test1
This model is a fine-tuned version of tiiuae/falcon-7b-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9608
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5166 | 0.85 | 200 | 1.5187 |
| 1.0449 | 1.71 | 400 | 1.1572 |
| 0.6828 | 2.56 | 600 | 0.9608 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
- License
- apache-2.0
- Created
- Jun 26, 2023
- Updated
- Jun 27, 2023