|
--- |
|
license: other |
|
base_model: Qwen/Qwen1.5-1.8B |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Qwen1.5_1.8B_ledgar |
|
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. --> |
|
|
|
# Qwen1.5_1.8B_ledgar |
|
|
|
This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5064 |
|
- Accuracy: 0.8669 |
|
- F1 Macro: 0.7902 |
|
- F1 Micro: 0.8669 |
|
|
|
## 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-06 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.3077 | 0.11 | 100 | 1.0945 | 0.7277 | 0.5771 | 0.7277 | |
|
| 0.8627 | 0.21 | 200 | 0.8368 | 0.7907 | 0.6657 | 0.7907 | |
|
| 0.7179 | 0.32 | 300 | 0.7824 | 0.7971 | 0.6862 | 0.7971 | |
|
| 0.6961 | 0.43 | 400 | 0.6952 | 0.8138 | 0.6992 | 0.8138 | |
|
| 0.745 | 0.53 | 500 | 0.6719 | 0.8121 | 0.7034 | 0.8121 | |
|
| 0.6505 | 0.64 | 600 | 0.6220 | 0.834 | 0.7469 | 0.834 | |
|
| 0.5914 | 0.75 | 700 | 0.6110 | 0.8362 | 0.7411 | 0.8362 | |
|
| 0.5837 | 0.85 | 800 | 0.5767 | 0.8385 | 0.7413 | 0.8385 | |
|
| 0.5218 | 0.96 | 900 | 0.5365 | 0.849 | 0.7703 | 0.849 | |
|
| 0.2632 | 1.07 | 1000 | 0.5504 | 0.8562 | 0.7684 | 0.8562 | |
|
| 0.2607 | 1.17 | 1100 | 0.5497 | 0.8525 | 0.7657 | 0.8525 | |
|
| 0.274 | 1.28 | 1200 | 0.5439 | 0.8584 | 0.7746 | 0.8584 | |
|
| 0.2216 | 1.39 | 1300 | 0.5687 | 0.8563 | 0.7754 | 0.8563 | |
|
| 0.2044 | 1.49 | 1400 | 0.5385 | 0.861 | 0.7820 | 0.861 | |
|
| 0.2508 | 1.6 | 1500 | 0.5658 | 0.8577 | 0.7711 | 0.8577 | |
|
| 0.2513 | 1.71 | 1600 | 0.5367 | 0.8589 | 0.7872 | 0.8589 | |
|
| 0.2787 | 1.81 | 1700 | 0.5133 | 0.8653 | 0.7903 | 0.8653 | |
|
| 0.2357 | 1.92 | 1800 | 0.5064 | 0.8669 | 0.7902 | 0.8669 | |
|
| 0.049 | 2.03 | 1900 | 0.5344 | 0.8719 | 0.7978 | 0.8719 | |
|
| 0.0298 | 2.13 | 2000 | 0.5762 | 0.8737 | 0.7992 | 0.8737 | |
|
| 0.0427 | 2.24 | 2100 | 0.5961 | 0.8708 | 0.7976 | 0.8708 | |
|
| 0.036 | 2.35 | 2200 | 0.6128 | 0.8728 | 0.7988 | 0.8728 | |
|
| 0.0551 | 2.45 | 2300 | 0.6165 | 0.8708 | 0.7976 | 0.8708 | |
|
| 0.0392 | 2.56 | 2400 | 0.6023 | 0.8749 | 0.8038 | 0.8749 | |
|
| 0.0364 | 2.67 | 2500 | 0.6168 | 0.8729 | 0.8001 | 0.8729 | |
|
| 0.0416 | 2.77 | 2600 | 0.6103 | 0.8753 | 0.8048 | 0.8753 | |
|
| 0.0353 | 2.88 | 2700 | 0.6118 | 0.8749 | 0.8054 | 0.8749 | |
|
| 0.0308 | 2.99 | 2800 | 0.6114 | 0.875 | 0.8057 | 0.875 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|