|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: petals-team/falcon-rw-1b |
|
model-index: |
|
- name: GenAI-task2-ModelB-DS |
|
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. --> |
|
|
|
# GenAI-task2-ModelB-DS |
|
|
|
This model is a fine-tuned version of [petals-team/falcon-rw-1b](https://huggingface.co/petals-team/falcon-rw-1b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7129 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.01 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.384 | 0.1 | 20 | 1.3865 | |
|
| 1.3566 | 0.2 | 40 | 1.2177 | |
|
| 1.1994 | 0.3 | 60 | 1.0759 | |
|
| 1.1201 | 0.4 | 80 | 0.9830 | |
|
| 0.8714 | 0.5 | 100 | 0.9083 | |
|
| 0.9164 | 0.6 | 120 | 0.8488 | |
|
| 0.7921 | 0.7 | 140 | 0.8116 | |
|
| 0.7861 | 0.8 | 160 | 0.7901 | |
|
| 0.8395 | 0.9 | 180 | 0.7645 | |
|
| 0.5803 | 1.0 | 200 | 0.7605 | |
|
| 0.8115 | 1.1 | 220 | 0.7420 | |
|
| 0.687 | 1.2 | 240 | 0.7307 | |
|
| 0.6314 | 1.3 | 260 | 0.7258 | |
|
| 0.8237 | 1.4 | 280 | 0.7206 | |
|
| 0.5456 | 1.5 | 300 | 0.7218 | |
|
| 0.8775 | 1.6 | 320 | 0.7158 | |
|
| 0.6114 | 1.7 | 340 | 0.7134 | |
|
| 0.668 | 1.8 | 360 | 0.7137 | |
|
| 0.756 | 1.9 | 380 | 0.7130 | |
|
| 0.5245 | 2.0 | 400 | 0.7129 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
