roberta_finetune_CPS_class_weights – AI Model by aminsamadi | AlphaNeural AI

You can deploy this model and start earning money today!

aminsamadi/
roberta_finetune_CPS_class_weights

like

0

generated_from_trainer

FacebookAI/roberta-base

Views

No views yet

roberta_finetune_CPS_class_weights

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

Loss: 1.8949
Accuracy: 0.7267
F1-micro: 0.7267
F1-macro: 0.6325

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1-micro	F1-macro
0.7524	1.0	736	1.0201	0.6812	0.6812	0.5511
0.732	2.0	1472	0.9168	0.7233	0.7233	0.6004
0.5315	3.0	2208	0.9742	0.7260	0.7260	0.5957
0.5015	4.0	2944	1.1334	0.7410	0.7410	0.6853
0.2782	5.0	3680	1.2754	0.7158	0.7158	0.6016
0.3866	6.0	4416	1.4692	0.7294	0.7294	0.6228
0.4302	7.0	5152	1.6980	0.7267	0.7267	0.6390
0.1895	8.0	5888	1.7853	0.7322	0.7322	0.6377
0.1945	9.0	6624	1.8803	0.7254	0.7254	0.6183
0.0963	10.0	7360	1.8949	0.7267	0.7267	0.6325

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1