gokuls/HBERTv1_48_L10_H512_A8
08
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
HBERTv148L10H512A8
This model is a fine-tuned version of [](https://huggingface.co/) on the gokuls/wikibookcorpuscompleteprocessedbertdataset dataset. It achieves the following results on the evaluation set:
- Loss: 2.8146
- Accuracy: 0.5044
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
- trainbatchsize: 64
- evalbatchsize: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- lrschedulerwarmup_steps: 10000
- num_epochs: 100
Training results
Framework versions
- Transformers 4.33.3
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.13.3