metadata
base_model: uer/gpt2-chinese-cluecorpussmall
tags:
- generated_from_trainer
model-index:
- name: similar_question_generation
results: []
similar_question_generation
This model is a fine-tuned version of uer/gpt2-chinese-cluecorpussmall on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0045
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 100.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2108 | 0.21 | 1000 | 2.0433 |
| 2.047 | 0.42 | 2000 | 2.0138 |
| 1.9859 | 0.63 | 3000 | 1.9939 |
| 1.9471 | 0.84 | 4000 | 1.9953 |
| 1.8932 | 1.05 | 5000 | 2.0034 |
| 1.8224 | 1.26 | 6000 | 1.9962 |
| 1.8131 | 1.47 | 7000 | 1.9886 |
| 1.8007 | 1.69 | 8000 | 1.9881 |
| 1.7948 | 1.9 | 9000 | 1.9825 |
| 1.7314 | 2.11 | 10000 | 2.0049 |
| 1.6901 | 2.32 | 11000 | 2.0029 |
| 1.6941 | 2.53 | 12000 | 2.0012 |
| 1.6921 | 2.74 | 13000 | 2.0024 |
| 1.6917 | 2.95 | 14000 | 2.0045 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0