bert-finetuned-comp2 – AI Model by brad1141 | AlphaNeural AI

You can deploy this model and start earning money today!

brad1141/
bert-finetuned-comp2

like

0

token-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-finetuned-comp2

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9570
Precision: 0.5169
Recall: 0.6765
F1: 0.5820
Accuracy: 0.5820

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: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.8434	1.0	934	0.7147	0.4475	0.6252	0.5096	0.5096
0.6307	2.0	1868	0.5959	0.5058	0.6536	0.5585	0.5585
0.4691	3.0	2802	0.6555	0.4761	0.6865	0.5521	0.5521
0.334	4.0	3736	0.7211	0.5292	0.6682	0.5863	0.5863
0.2326	5.0	4670	0.8046	0.4886	0.6865	0.5682	0.5682
0.1625	6.0	5604	0.8650	0.4972	0.6851	0.5728	0.5728
0.1195	7.0	6538	0.9570	0.5169	0.6765	0.5820	0.5820

Framework versions

Transformers 4.17.0
Pytorch 1.10.0+cu111
Datasets 2.0.0
Tokenizers 0.11.6