Downloads · 30 days
8
4% of all-time downloads
HBERTv1_48_L8_H256_A4
gokuls/HBERTv1_48_L8_H256_A4
HBERTv1_48_L8_H256_A4 is a fill-mask model from gokuls. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
185
Public
Repo size
92 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin92 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- Sep 29, 2023
- Updated
- Oct 2, 2023
- SHA
- c809032a
Try a prompt
Model card
From the Hugging Face model README
<!-- 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. -->
HBERTv1_48_L8_H256_A4
This model is a fine-tuned version of on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 4.5723
- Accuracy: 0.2961
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: 96
- eval_batch_size: 96
- 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: 100
Training results
Framework versions
- Transformers 4.33.3
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Fill-Mask
- Library
- transformers
- Type
- hybridbert
- Created
- Sep 29, 2023
- Updated
- Oct 2, 2023