Downloads · 30 days
0
phi-3-small-sft-lora
realsanjeev/phi-3-small-sft-lora
phi-3-small-sft-lora is a machine learning model from realsanjeev. 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 mit.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated May 24, 2024
Repo size
101 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors50.3 MB · 96%
At a glance
- License
- mit
- Access
- Public
- Created
- May 24, 2024
- Updated
- May 24, 2024
- SHA
- 56b306c2
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. -->
phi-3-small-sft-lora
This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.2964
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6299 | 1.0 | 1 | 1.2966 |
| 0.6065 | 1.9692 | 2 | 1.2964 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- License
- mit
- Created
- May 24, 2024
- Updated
- May 24, 2024