|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: microsoft/phi-2 |
|
model-index: |
|
- name: phi2-dolly-sum-finetune |
|
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. --> |
|
|
|
# phi2-dolly-sum-finetune |
|
|
|
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0505 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- training_steps: 500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.9329 | 0.05 | 25 | 2.4178 | |
|
| 2.4832 | 0.09 | 50 | 2.1541 | |
|
| 2.1688 | 0.14 | 75 | 2.0774 | |
|
| 2.2247 | 0.18 | 100 | 2.0725 | |
|
| 2.225 | 0.23 | 125 | 2.0652 | |
|
| 2.2217 | 0.27 | 150 | 2.0635 | |
|
| 2.2282 | 0.32 | 175 | 2.0611 | |
|
| 2.1104 | 0.37 | 200 | 2.0608 | |
|
| 2.1583 | 0.41 | 225 | 2.0569 | |
|
| 2.1197 | 0.46 | 250 | 2.0565 | |
|
| 2.1257 | 0.5 | 275 | 2.0559 | |
|
| 2.0018 | 0.55 | 300 | 2.0512 | |
|
| 2.0203 | 0.6 | 325 | 2.0546 | |
|
| 2.1332 | 0.64 | 350 | 2.0519 | |
|
| 2.1585 | 0.69 | 375 | 2.0503 | |
|
| 2.1287 | 0.73 | 400 | 2.0510 | |
|
| 2.1431 | 0.78 | 425 | 2.0515 | |
|
| 2.1601 | 0.82 | 450 | 2.0522 | |
|
| 2.088 | 0.87 | 475 | 2.0481 | |
|
| 2.0462 | 0.92 | 500 | 2.0505 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.1 |
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
