Downloads · 30 days
6
17% of all-time downloads
sft-microsoft-phi2-on-dialogsum
xck2020/sft-microsoft-phi2-on-dialogsum
sft-microsoft-phi2-on-dialogsum is a machine learning model from xck2020. 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
35
Public
Repo size
94.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors94.4 MB · 98%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Oct 19, 2024
- Updated
- Oct 19, 2024
- SHA
- c2246c7a
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. -->
sft-microsoft-phi2-on-dialogsum
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3644
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 10
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.2357 | 5.0 | 50 | 1.4088 |
| 6.5339 | 10.0 | 100 | 1.3644 |
Framework versions
- PEFT 0.7.1
- Transformers 4.46.0.dev0
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.20.1
- Library
- peft
- License
- mit
- Created
- Oct 19, 2024
- Updated
- Oct 19, 2024