add_bert_12_layer_model_complete_training_new_48
This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.7593
- Accuracy: 0.1584
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 |
---|---|---|---|---|
6.1015 | 0.08 | 10000 | 6.0525 | 0.1516 |
6.101 | 0.16 | 20000 | 6.0321 | 0.1517 |
5.9404 | 0.25 | 30000 | 5.9942 | 0.1528 |
5.9754 | 0.33 | 40000 | 5.9490 | 0.1537 |
5.9035 | 0.41 | 50000 | 5.8952 | 0.1546 |
5.8787 | 0.49 | 60000 | 5.8524 | 0.1556 |
5.7845 | 0.57 | 70000 | 5.8146 | 0.1568 |
5.8335 | 0.66 | 80000 | 5.7857 | 0.1575 |
5.7803 | 0.74 | 90000 | 5.7593 | 0.1584 |
Framework versions
- Transformers 4.30.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 5
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.