bert-concat-3 – AI Model by NasimB | AlphaNeural AI

You can deploy this model and start earning money today!

NasimB/
bert-concat-3

like

0

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-concat-3

This model is a fine-tuned version of on the generator dataset. It achieves the following results on the evaluation set:

Loss: 5.8028

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: 0.0005
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
num_epochs: 35
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
6.5215	2.11	1000	6.1057
5.9958	4.22	2000	6.0199
5.9066	6.33	3000	5.9833
5.8449	8.44	4000	5.9594
5.7913	10.55	5000	5.9176
5.7418	12.66	6000	5.8949
5.6901	14.77	7000	5.8753
5.6485	16.88	8000	5.8592
5.6238	18.99	9000	5.8509
5.6704	21.1	10000	5.8856
5.6375	23.21	11000	5.8703
5.6039	25.32	12000	5.8635
5.5756	27.43	13000	5.8533
5.5437	29.54	14000	5.8408
5.5189	31.65	15000	5.8154
5.4982	33.76	16000	5.8028

Framework versions

Transformers 4.26.1
Pytorch 1.11.0+cu113
Datasets 2.13.0
Tokenizers 0.13.3