small-mlm-glue-sst2-from-scratch-custom-tokenizer-expand-vocab – AI Model by muhtasham | AlphaNeural AI

You can deploy this model and start earning money today!

muhtasham/
small-mlm-glue-sst2-from-scratch-custom-tokenizer-expand-vocab

like

0

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

small-mlm-glue-sst2-from-scratch-custom-tokenizer-expand-vocab

This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:

Loss: 6.2435

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss
7.9024	0.4	500	6.7698
6.841	0.8	1000	6.5930
6.6281	1.2	1500	6.5066
6.5663	1.6	2000	6.3862
6.4527	2.0	2500	6.2757
6.381	2.4	3000	6.3472
6.2872	2.8	3500	6.2887
6.232	3.2	4000	6.2333
6.1222	3.6	4500	6.2479
6.1138	4.0	5000	6.2435

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.13.1+cu116
Datasets 2.9.1.dev0
Tokenizers 0.13.2