|
--- |
|
license: other |
|
base_model: Qwen/Qwen1.5-1.8B |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Qwen1.5_1.8B_patent |
|
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_patent |
|
|
|
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: 0.8989 |
|
- Accuracy: 0.6976 |
|
- F1 Macro: 0.6507 |
|
- F1 Micro: 0.6976 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.4469 | 0.13 | 50 | 1.3521 | 0.528 | 0.3842 | 0.528 | |
|
| 1.1465 | 0.26 | 100 | 1.1614 | 0.596 | 0.4991 | 0.596 | |
|
| 1.1717 | 0.38 | 150 | 1.0561 | 0.6286 | 0.5523 | 0.6286 | |
|
| 0.9861 | 0.51 | 200 | 0.9592 | 0.6682 | 0.5813 | 0.6682 | |
|
| 0.9701 | 0.64 | 250 | 0.9579 | 0.6658 | 0.5949 | 0.6658 | |
|
| 0.9389 | 0.77 | 300 | 0.9364 | 0.679 | 0.6287 | 0.679 | |
|
| 0.9914 | 0.9 | 350 | 0.9246 | 0.6756 | 0.6115 | 0.6756 | |
|
| 0.7508 | 1.02 | 400 | 0.9047 | 0.6812 | 0.6406 | 0.6812 | |
|
| 0.6312 | 1.15 | 450 | 0.9342 | 0.6844 | 0.6410 | 0.6844 | |
|
| 0.6436 | 1.28 | 500 | 0.9464 | 0.6848 | 0.6410 | 0.6848 | |
|
| 0.6429 | 1.41 | 550 | 0.9366 | 0.6846 | 0.6299 | 0.6846 | |
|
| 0.6471 | 1.53 | 600 | 0.9347 | 0.6812 | 0.6490 | 0.6812 | |
|
| 0.7045 | 1.66 | 650 | 0.9457 | 0.6696 | 0.6265 | 0.6696 | |
|
| 0.6311 | 1.79 | 700 | 0.9206 | 0.6924 | 0.6303 | 0.6924 | |
|
| 0.6659 | 1.92 | 750 | 0.8989 | 0.6976 | 0.6507 | 0.6976 | |
|
| 0.2872 | 2.05 | 800 | 1.0101 | 0.6888 | 0.6524 | 0.6888 | |
|
| 0.2666 | 2.17 | 850 | 1.1459 | 0.6824 | 0.6384 | 0.6824 | |
|
| 0.3211 | 2.3 | 900 | 1.1165 | 0.6704 | 0.6362 | 0.6704 | |
|
| 0.2831 | 2.43 | 950 | 1.1722 | 0.6698 | 0.6360 | 0.6698 | |
|
| 0.2545 | 2.56 | 1000 | 1.2073 | 0.6714 | 0.6459 | 0.6714 | |
|
| 0.2069 | 2.69 | 1050 | 1.1839 | 0.6798 | 0.6438 | 0.6798 | |
|
| 0.2109 | 2.81 | 1100 | 1.1677 | 0.6778 | 0.6443 | 0.6778 | |
|
| 0.2383 | 2.94 | 1150 | 1.1807 | 0.6776 | 0.6462 | 0.6776 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|