hs768-nh32-nl12_custom
This model is a fine-tuned version of on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 1.1028
- Accuracy: 0.7562
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.4572 | 1.39 | 500 | 1.4515 | 0.6198 |
1.3474 | 2.78 | 1000 | 1.1752 | 0.6813 |
0.8943 | 4.17 | 1500 | 1.0905 | 0.7531 |
0.6586 | 5.56 | 2000 | 1.0099 | 0.7703 |
0.5037 | 6.94 | 2500 | 1.0151 | 0.7742 |
0.3785 | 8.33 | 3000 | 1.0359 | 0.8003 |
0.2963 | 9.72 | 3500 | 1.0788 | 0.8096 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0
- Downloads last month
- 3