amazon_helpfulness_classification_on_TAPT_full_pretrained_best_epoch_f1 – AI Model by ltuzova | AlphaNeural AI

You can deploy this model and start earning money today!

ltuzova/
amazon_helpfulness_classification_on_TAPT_full_pretrained_best_epoch_f1

like

0

text-classification

generated_from_trainer

BigTMiami/tapt_helpfulness_base_pretraining_model

autotrain_compatible

endpoints_compatible

Views

No views yet

amazon_helpfulness_classification_on_TAPT_full_pretrained_best_epoch_f1

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

Loss: 0.3236
Accuracy: 0.8782
F1 Macro: 0.6889

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
0.3243	1.0	7204	0.3113	0.8682	0.6013
0.3096	2.0	14408	0.3569	0.8692	0.5975
0.2887	3.0	21612	0.3255	0.8766	0.6939
0.2496	4.0	28816	0.3717	0.8706	0.6589
0.1811	5.0	36020	0.4893	0.8688	0.6844
0.1767	6.0	43224	0.6158	0.8628	0.6793

Framework versions

Transformers 4.36.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2