add_bert_12_layer_model_complete_training_new_120
This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new_96 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.2619
- Accuracy: 0.2063
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
5.4864 | 0.08 | 10000 | 5.4102 | 0.1898 |
5.4838 | 0.16 | 20000 | 5.3944 | 0.1919 |
5.2956 | 0.25 | 30000 | 5.3816 | 0.1933 |
5.418 | 0.33 | 40000 | 5.3667 | 0.1948 |
5.3825 | 0.41 | 50000 | 5.3490 | 0.1968 |
5.3783 | 0.49 | 60000 | 5.3301 | 0.1988 |
5.2869 | 0.57 | 70000 | 5.3140 | 0.2001 |
5.3668 | 0.66 | 80000 | 5.2981 | 0.2022 |
5.2709 | 0.74 | 90000 | 5.2782 | 0.2043 |
5.3297 | 0.82 | 100000 | 5.2619 | 0.2063 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.