amazon_helpfulness_classification_on_TAPT_pretrained_no_condencing – AI Model by ltuzova | AlphaNeural AI

You can deploy this model and start earning money today!

ltuzova/
amazon_helpfulness_classification_on_TAPT_pretrained_no_condencing

like

0

text-classification

generated_from_trainer

ltuzova/tapt_helpfulness_base_pretraining_no_condencing

autotrain_compatible

endpoints_compatible

Views

No views yet

amazon_helpfulness_classification_on_TAPT_pretrained_no_condencing

This model is a fine-tuned version of ltuzova/tapt_helpfulness_base_pretraining_no_condencing on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4784
Accuracy: 0.8717
F1 Macro: 0.6875

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=(0.9,0.98) and epsilon=1e-06
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
0.3231	1.0	7204	0.3108	0.871	0.6266
0.328	2.0	14408	0.3420	0.8694	0.5911
0.296	3.0	21612	0.3209	0.8724	0.6628
0.2654	4.0	28816	0.3918	0.8708	0.6563
0.1966	5.0	36020	0.4985	0.868	0.6848
0.1595	6.0	43224	0.5824	0.8676	0.6815
0.157	7.0	50428	0.5886	0.8658	0.6686
0.1299	8.0	57632	0.7385	0.8626	0.6697

Framework versions

Transformers 4.36.2
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.15.2