results – AI Model by AgentDS | AlphaNeural AI

You can deploy this model and start earning money today!

AgentDS/
results

like

0

generated_from_trainer

FacebookAI/roberta-base

Views

No views yet

results

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

Loss: 0.1755

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-06
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.6937	1.0	130	0.6936
0.6782	2.0	260	0.6684
0.3968	3.0	390	0.3106
0.3238	4.0	520	0.2410
0.2817	5.0	650	0.1915
0.1955	6.0	780	0.2092
0.1536	7.0	910	0.1763
0.1352	8.0	1040	0.1755
0.1266	9.0	1170	0.1853
0.1115	10.0	1300	0.1805

Framework versions

Transformers 4.41.2
Pytorch 2.0.1
Datasets 2.14.6
Tokenizers 0.19.1