|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: tiiuae/falcon-7b-instruct |
|
model-index: |
|
- name: Falcon-7b-Finetuned-Extented-MBPP-Dataset-Synthetic |
|
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. --> |
|
|
|
# Falcon-7b-Finetuned-Extented-MBPP-Dataset-Synthetic |
|
|
|
This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9466 |
|
|
|
## 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-06 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.9771 | 0.18 | 500 | 1.6788 | |
|
| 0.9972 | 0.36 | 1000 | 1.2072 | |
|
| 1.0858 | 0.53 | 1500 | 1.0909 | |
|
| 0.8945 | 0.71 | 2000 | 1.0609 | |
|
| 0.5405 | 0.89 | 2500 | 1.0325 | |
|
| 1.3803 | 1.07 | 3000 | 1.0174 | |
|
| 0.4474 | 1.25 | 3500 | 1.0085 | |
|
| 0.635 | 1.43 | 4000 | 1.0013 | |
|
| 0.3225 | 1.6 | 4500 | 0.9901 | |
|
| 0.6406 | 1.78 | 5000 | 0.9893 | |
|
| 0.7074 | 1.96 | 5500 | 0.9835 | |
|
| 0.577 | 2.14 | 6000 | 0.9836 | |
|
| 0.7014 | 2.32 | 6500 | 0.9718 | |
|
| 0.9365 | 2.49 | 7000 | 0.9651 | |
|
| 0.9926 | 2.67 | 7500 | 0.9637 | |
|
| 0.5796 | 2.85 | 8000 | 0.9621 | |
|
| 1.1842 | 3.03 | 8500 | 0.9601 | |
|
| 0.8448 | 3.21 | 9000 | 0.9572 | |
|
| 0.3799 | 3.39 | 9500 | 0.9496 | |
|
| 0.6202 | 3.56 | 10000 | 0.9514 | |
|
| 0.5857 | 3.74 | 10500 | 0.9521 | |
|
| 0.6707 | 3.92 | 11000 | 0.9497 | |
|
| 0.5089 | 4.1 | 11500 | 0.9480 | |
|
| 0.4459 | 4.28 | 12000 | 0.9472 | |
|
| 0.5792 | 4.45 | 12500 | 0.9469 | |
|
| 0.1743 | 4.63 | 13000 | 0.9467 | |
|
| 0.7094 | 4.81 | 13500 | 0.9465 | |
|
| 0.4949 | 4.99 | 14000 | 0.9466 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.15.2 |
