Downloads · 30 days
0
finetuningLLMs-project-phi-1.5
ssuzana/finetuningLLMs-project-phi-1.5
finetuningLLMs-project-phi-1.5 is a machine learning model from ssuzana. 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 other.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Nov 4, 2023
Repo size
12.6 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin6.3 MB · 39%
At a glance
- License
- other
- Access
- Public
- Created
- Nov 4, 2023
- Updated
- Nov 4, 2023
- SHA
- a6da4942
Base models
Datasets
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. -->
finetuningLLMs-project-phi-1.5
This model is a fine-tuned version of microsoft/phi-1_5 on the scitldr dataset. It achieves the following results on the evaluation set:
- Loss: 2.5345
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: 0.001
- train_batch_size: 1
- eval_batch_size: 1
- 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 |
|---|---|---|---|
| 2.5536 | 0.1 | 200 | 2.5953 |
| 2.5736 | 0.2 | 400 | 2.5918 |
| 2.5299 | 0.3 | 600 | 2.5771 |
| 2.5857 | 0.4 | 800 | 2.5693 |
| 2.545 | 0.5 | 1000 | 2.5584 |
| 2.5732 | 0.6 | 1200 | 2.5525 |
| 2.5481 | 0.7 | 1400 | 2.5461 |
| 2.5276 | 0.8 | 1600 | 2.5396 |
| 2.578 | 0.9 | 1800 | 2.5345 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- other
- Created
- Nov 4, 2023
- Updated
- Nov 4, 2023