results_roberta – AI Model by Taniosama | AlphaNeural AI

You can deploy this model and start earning money today!

Taniosama/
results_roberta

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

results_roberta

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

Loss: 0.4870

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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.4672	1.0	74	2.3262
2.4163	2.0	148	1.3214
1.1959	3.0	222	0.8632
0.9312	4.0	296	0.7046
0.6355	5.0	370	0.6192
0.5981	6.0	444	0.5560
0.4621	7.0	518	0.5440
0.4467	8.0	592	0.5017
0.399	9.0	666	0.4906
0.3826	10.0	740	0.4870

Framework versions

Transformers 4.55.2
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2