sa_bert_12_layer_modified_complete_training_72

gokuls/sa_bert_12_layer_modified_complete_training_72

sa_bert_12_layer_modified_complete_training_72 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. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

178

Public

Repo size

4.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin495 MB · 95%

At a glance

Task: Fill-Mask
Library: transformers
Model type: hybridbert
Access: Public
Created: Jul 10, 2023
Updated: Jul 11, 2023
SHA: 1565d4a9

Try a prompt

Model card

From the Hugging Face model README

sa_bert_12_layer_modified_complete_training_72

This model is a fine-tuned version of gokuls/sa_bert_12_layer_modified_complete_training_48 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.6236
Accuracy: 0.5322

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: 32
eval_batch_size: 32
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
3.0311	0.05	10000	2.8263	0.5069
2.8816	0.11	20000	2.7833	0.5126
2.7734	0.16	30000	2.7565	0.5158
2.7612	0.22	40000	2.7284	0.5196
2.8843	0.27	50000	2.7006	0.5229
2.7809	0.33	60000	2.6765	0.5254
2.6683	0.38	70000	2.6580	0.5276
2.7175	0.44	80000	2.6270	0.5316
2.8903	0.49	90000	2.6236	0.5322

Framework versions

Transformers 4.30.2
Pytorch 1.14.0a0+410ce96
Datasets 2.13.1
Tokenizers 0.13.3

Task: Fill-Mask
Library: transformers
Type: hybridbert
Created: Jul 10, 2023
Updated: Jul 11, 2023