Downloads · 30 days
3
23% of all-time downloads
phi2_fine_tuned
ArunaMak/phi2_fine_tuned
phi2_fine_tuned is a machine learning model from ArunaMak. 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
13
Public
Repo size
3.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.2 GB · 100%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 1, 2024
- Updated
- Aug 1, 2024
- SHA
- d8fefb33
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. -->
ERC_SUMMARY_phi2_peft
This model is a fine-tuned version of microsoft/phi-2 on the ArunaMak/ERC_summary dataset. It achieves the following results on the evaluation set:
- Loss: 1.4798
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5888 | 1.0 | 40 | 1.5819 |
| 1.5677 | 2.0 | 80 | 1.5202 |
| 1.5819 | 3.0 | 120 | 1.4962 |
| 1.4227 | 4.0 | 160 | 1.4842 |
| 1.4786 | 5.0 | 200 | 1.4798 |
| 1.5015 | 6.0 | 240 | 1.4798 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.0.dev0
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Library
- peft
- License
- mit
- Created
- Aug 1, 2024
- Updated
- Aug 1, 2024