roberta-base_fine_lr0.0005_bs4_epoch20_wd0.01 – AI Model by jysssacc | AlphaNeural AI

You can deploy this model and start earning money today!

jysssacc/
roberta-base_fine_lr0.0005_bs4_epoch20_wd0.01

like

0

text-generation

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

roberta-base_fine_lr0.0005_bs4_epoch20_wd0.01

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

Loss: 0.2481

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: 0.0005
train_batch_size: 4
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: 500
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
4.2947	1.0	157	0.3204
0.6822	2.0	314	0.3902
1.0581	3.0	471	1.2741
1.7083	4.0	628	1.5418
1.4489	5.0	785	1.5167
1.1426	6.0	942	1.5120
0.9551	7.0	1099	1.3990
0.8032	8.0	1256	1.2418
0.5758	9.0	1413	0.9339
0.5078	10.0	1570	1.1084
0.3889	11.0	1727	0.8454
0.2517	12.0	1884	0.8793
0.232	13.0	2041	0.8882
0.1593	14.0	2198	0.6870
0.1067	15.0	2355	0.5925
0.0887	16.0	2512	0.6818
0.0522	17.0	2669	0.4197
0.1269	18.0	2826	0.2809
0.0131	19.0	2983	0.2587
0.0168	20.0	3140	0.2481

Framework versions

Transformers 4.36.2
Pytorch 2.0.1
Datasets 2.16.1
Tokenizers 0.15.0