bert-goemotions-10epochs-run5 – AI Model by mpalaval | AlphaNeural AI

You can deploy this model and start earning money today!

mpalaval/
bert-goemotions-10epochs-run5

like

0

generated_from_trainer

google-bert/bert-base-uncased

endpoints_compatible

Views

No views yet

bert-goemotions-10epochs-run5

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1699
Accuracy Thresh: 0.9478
F1 weighted: 0.3214
F1 macro: 0.2568
Accuracy: 0.3159
Recall weighted: 0.3159
Recall macro: 0.2830

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Thresh	F1 weighted	F1 macro	Accuracy	Recall weighted	Recall macro
0.0641	1.0	10558	0.1495	0.9525	0.3589	0.2877	0.3579	0.3579	0.3107
0.059	2.0	21116	0.1485	0.9517	0.3512	0.2834	0.3472	0.3472	0.3064
0.0624	3.0	31674	0.1596	0.9505	0.3426	0.2708	0.3411	0.3411	0.2892
0.0602	4.0	42232	0.1671	0.9474	0.3294	0.2678	0.3238	0.3238	0.2946
0.0593	5.0	52790	0.1697	0.9481	0.3308	0.2599	0.3278	0.3278	0.2834
0.0645	6.0	63348	0.1440	0.9532	0.3419	0.2772	0.3405	0.3405	0.3053
0.075	7.0	73906	0.1501	0.9516	0.3362	0.2682	0.3324	0.3324	0.2909
0.0721	8.0	84464	0.1570	0.9501	0.3292	0.2613	0.3249	0.3249	0.2843
0.0695	9.0	95022	0.1627	0.9492	0.3252	0.2600	0.3214	0.3214	0.2861
0.0672	10.0	105580	0.1699	0.9478	0.3214	0.2568	0.3159	0.3159	0.2830

Framework versions

Transformers 4.35.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1