|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
base_model: microsoft/phi-2 |
|
model-index: |
|
- name: delphi |
|
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. --> |
|
|
|
# delphi |
|
|
|
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the alpaca_gpt4_en dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8625 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 1.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.0325 | 0.07 | 200 | 0.8922 | |
|
| 0.9136 | 0.14 | 400 | 0.8801 | |
|
| 0.9043 | 0.21 | 600 | 0.8753 | |
|
| 0.8903 | 0.27 | 800 | 0.8711 | |
|
| 0.9056 | 0.34 | 1000 | 0.8683 | |
|
| 0.9001 | 0.41 | 1200 | 0.8673 | |
|
| 0.8949 | 0.48 | 1400 | 0.8668 | |
|
| 0.8917 | 0.55 | 1600 | 0.8656 | |
|
| 0.8951 | 0.62 | 1800 | 0.8648 | |
|
| 0.9014 | 0.68 | 2000 | 0.8637 | |
|
| 0.8874 | 0.75 | 2200 | 0.8630 | |
|
| 0.8968 | 0.82 | 2400 | 0.8628 | |
|
| 0.8755 | 0.89 | 2600 | 0.8626 | |
|
| 0.9029 | 0.96 | 2800 | 0.8625 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.15.0 |
