|
--- |
|
language: |
|
- en |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- Open-Orca22/OpenOrca22 |
|
base_model: microsoft/phi-2 |
|
model-index: |
|
- name: phi-2 |
|
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. --> |
|
|
|
# phi-2 |
|
|
|
This model is a fine-tuned version of [microsoftl](https://huggingface.co/microsoftl) on the Open-Orca22/OpenOrca22 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6236 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 5 |
|
- training_steps: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.0884 | 0.2 | 50 | 1.9608 | |
|
| 2.0157 | 0.4 | 100 | 1.7828 | |
|
| 1.6203 | 0.6 | 150 | 1.7023 | |
|
| 1.7122 | 0.8 | 200 | 1.6731 | |
|
| 1.6622 | 1.0 | 250 | 1.6593 | |
|
| 1.6149 | 1.2 | 300 | 1.6532 | |
|
| 1.5907 | 1.4 | 350 | 1.6480 | |
|
| 1.5713 | 1.6 | 400 | 1.6429 | |
|
| 1.5579 | 1.8 | 450 | 1.6394 | |
|
| 1.6403 | 2.0 | 500 | 1.6361 | |
|
| 1.6505 | 2.2 | 550 | 1.6334 | |
|
| 1.5505 | 2.4 | 600 | 1.6315 | |
|
| 1.5232 | 2.6 | 650 | 1.6300 | |
|
| 1.6129 | 2.8 | 700 | 1.6278 | |
|
| 1.5062 | 3.0 | 750 | 1.6267 | |
|
| 1.6031 | 3.2 | 800 | 1.6254 | |
|
| 1.5404 | 3.4 | 850 | 1.6254 | |
|
| 1.6157 | 3.6 | 900 | 1.6242 | |
|
| 1.5541 | 3.8 | 950 | 1.6238 | |
|
| 1.471 | 4.0 | 1000 | 1.6236 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
