Downloads · 30 days
4
8% of all-time downloads
Phi-3.5-MultiCap-tool-embedding-step2
sofyc/Phi-3.5-MultiCap-tool-embedding-step2
Phi-3.5-MultiCap-tool-embedding-step2 is a machine learning model from sofyc. 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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
48
Public
Repo size
35.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors35.7 MB · 95%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Sep 12, 2024
- Updated
- Sep 12, 2024
- SHA
- 0b8977be
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. -->
Phi-3.5-MultiCap-tool-embedding-step2
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4993
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4928 | 0.2256 | 50 | 0.5051 |
| 0.4781 | 0.4512 | 100 | 0.5038 |
| 0.4741 | 0.6768 | 150 | 0.5022 |
| 0.5298 | 0.9024 | 200 | 0.5017 |
| 0.4718 | 1.1280 | 250 | 0.5010 |
| 0.466 | 1.3536 | 300 | 0.4999 |
| 0.4393 | 1.5792 | 350 | 0.5004 |
| 0.4861 | 1.8049 | 400 | 0.4996 |
| 0.4781 | 2.0305 | 450 | 0.4996 |
| 0.4251 | 2.2561 | 500 | 0.4997 |
| 0.4697 | 2.4817 | 550 | 0.4995 |
| 0.4768 | 2.7073 | 600 | 0.4996 |
| 0.4906 | 2.9329 | 650 | 0.4993 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 3.0.0
- Tokenizers 0.19.1
- Library
- peft
- License
- mit
- Created
- Sep 12, 2024
- Updated
- Sep 12, 2024