|
--- |
|
license: other |
|
base_model: Qwen/Qwen1.5-1.8B |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Qwen1.5_1.8B_twitter |
|
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_twitter |
|
|
|
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: 0.5039 |
|
- Accuracy: 0.7776 |
|
- F1 Macro: 0.7420 |
|
- F1 Micro: 0.7776 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 32 |
|
- total_eval_batch_size: 32 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 0.6585 | 0.18 | 50 | 0.6435 | 0.7123 | 0.5811 | 0.7123 | |
|
| 0.6396 | 0.37 | 100 | 0.6016 | 0.7298 | 0.6998 | 0.7298 | |
|
| 0.5108 | 0.55 | 150 | 0.5227 | 0.7528 | 0.6963 | 0.7528 | |
|
| 0.5065 | 0.74 | 200 | 0.5503 | 0.7417 | 0.6347 | 0.7417 | |
|
| 0.4883 | 0.92 | 250 | 0.5039 | 0.7776 | 0.7420 | 0.7776 | |
|
| 0.3296 | 1.1 | 300 | 0.5250 | 0.7730 | 0.7307 | 0.7730 | |
|
| 0.322 | 1.29 | 350 | 0.5510 | 0.7721 | 0.7423 | 0.7721 | |
|
| 0.3287 | 1.47 | 400 | 0.5392 | 0.7583 | 0.6932 | 0.7583 | |
|
| 0.3097 | 1.65 | 450 | 0.5631 | 0.7629 | 0.7223 | 0.7629 | |
|
| 0.3397 | 1.84 | 500 | 0.5669 | 0.7675 | 0.7334 | 0.7675 | |
|
| 0.2618 | 2.02 | 550 | 0.5891 | 0.75 | 0.6870 | 0.75 | |
|
| 0.1745 | 2.21 | 600 | 0.6400 | 0.7583 | 0.7123 | 0.7583 | |
|
| 0.1572 | 2.39 | 650 | 0.6694 | 0.7518 | 0.6967 | 0.7518 | |
|
| 0.1804 | 2.57 | 700 | 0.6870 | 0.7610 | 0.7173 | 0.7610 | |
|
| 0.1817 | 2.76 | 750 | 0.6656 | 0.7537 | 0.7045 | 0.7537 | |
|
| 0.1984 | 2.94 | 800 | 0.6783 | 0.7518 | 0.6949 | 0.7518 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
