albert-base-chinese-finetuned-qqp
This model is a fine-tuned version of ckiplab/albert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.19846130907535553
- Accuracy: 0.925531914893617
- F1: 0.9263157894736843
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 30 | 0.691918 | 0.617021 | 0.647059 |
| No log | 2.0 | 60 | 0.629044 | 0.819149 | 0.813187 |
| No log | 3.0 | 90 | 0.340141 | 0.882979 | 0.893204 |
| No log | 4.0 | 120 | 0.198461 | 0.925532 | 0.926316 |
| No log | 5.0 | 150 | 0.171799 | 0.925532 | 0.926316 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.0.dev0
- Downloads last month
- 9