roberta-large-anion-1e-06-256 – AI Model by mhr2004 | AlphaNeural AI

You can deploy this model and start earning money today!

mhr2004/
roberta-large-anion-1e-06-256

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-large

autotrain_compatible

endpoints_compatible

Views

No views yet

roberta-large-anion-1e-06-256

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

Loss: 0.2359

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: 1e-06
train_batch_size: 256
eval_batch_size: 256
seed: 42
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: 30

Training results

Training Loss	Epoch	Step	Validation Loss
0.7025	1.0	358	0.4381
0.4222	2.0	716	0.3365
0.3481	3.0	1074	0.3071
0.3088	4.0	1432	0.2723
0.2942	5.0	1790	0.2667
0.2692	6.0	2148	0.2565
0.2495	7.0	2506	0.2506
0.231	8.0	2864	0.2441
0.2158	9.0	3222	0.2322
0.2118	10.0	3580	0.2333
0.2016	11.0	3938	0.2357
0.1909	12.0	4296	0.2359

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.3.2
Tokenizers 0.21.1