|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: microsoft/phi-2 |
|
model-index: |
|
- name: sft-microsoft-phi2-on-memory_dialoges |
|
results: [] |
|
--- |
|
|
|
<!-- 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-memory_dialoges |
|
|
|
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6715 |
|
|
|
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- training_steps: 500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.0517 | 0.2 | 20 | 1.9505 | |
|
| 1.7337 | 0.4 | 40 | 1.2702 | |
|
| 0.9881 | 0.6 | 60 | 0.8091 | |
|
| 0.7869 | 0.8 | 80 | 0.7450 | |
|
| 0.7454 | 0.99 | 100 | 0.7252 | |
|
| 0.7128 | 1.19 | 120 | 0.7143 | |
|
| 0.7142 | 1.39 | 140 | 0.7064 | |
|
| 0.6921 | 1.59 | 160 | 0.7011 | |
|
| 0.688 | 1.79 | 180 | 0.6962 | |
|
| 0.7061 | 1.99 | 200 | 0.6918 | |
|
| 0.6744 | 2.19 | 220 | 0.6898 | |
|
| 0.6771 | 2.39 | 240 | 0.6854 | |
|
| 0.6795 | 2.58 | 260 | 0.6833 | |
|
| 0.661 | 2.78 | 280 | 0.6802 | |
|
| 0.6596 | 2.98 | 300 | 0.6793 | |
|
| 0.6431 | 3.18 | 320 | 0.6780 | |
|
| 0.6604 | 3.38 | 340 | 0.6766 | |
|
| 0.6404 | 3.58 | 360 | 0.6757 | |
|
| 0.6571 | 3.78 | 380 | 0.6740 | |
|
| 0.6611 | 3.98 | 400 | 0.6733 | |
|
| 0.6381 | 4.17 | 420 | 0.6732 | |
|
| 0.6372 | 4.37 | 440 | 0.6721 | |
|
| 0.639 | 4.57 | 460 | 0.6718 | |
|
| 0.6506 | 4.77 | 480 | 0.6717 | |
|
| 0.6226 | 4.97 | 500 | 0.6715 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.1 |
