phi-3-mini-LoRA
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4578
Platform - *** Trained on Google Colab ***
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.9205 | 0.2022 | 100 | 0.9239 |
0.6297 | 0.4044 | 200 | 0.6279 |
0.4782 | 0.6067 | 300 | 0.5032 |
0.494 | 0.8089 | 400 | 0.4833 |
0.4613 | 1.0111 | 500 | 0.4755 |
0.4587 | 1.2133 | 600 | 0.4708 |
0.4643 | 1.4156 | 700 | 0.4673 |
0.4498 | 1.6178 | 800 | 0.4645 |
0.506 | 1.8200 | 900 | 0.4624 |
0.4235 | 2.0222 | 1000 | 0.4608 |
0.4798 | 2.2245 | 1100 | 0.4597 |
0.4646 | 2.4267 | 1200 | 0.4586 |
0.4636 | 2.6289 | 1300 | 0.4580 |
0.4596 | 2.8311 | 1400 | 0.4578 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for dhanishetty/phi-3-mini-QLoRA_Adapters
Base model
microsoft/Phi-3-mini-4k-instruct
Adapter
this model