distilr-lr1e05-wd0.01-bs32 – AI Model by paola-md | AlphaNeural AI

You can deploy this model and start earning money today!

paola-md/
distilr-lr1e05-wd0.01-bs32

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

distilr-lr1e05-wd0.01-bs32

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

Loss: 0.2746
Rmse: 0.5241
Mse: 0.2746
Mae: 0.4153

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-05
train_batch_size: 256
eval_batch_size: 256
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse	Mse	Mae
0.2769	1.0	623	0.2740	0.5234	0.2740	0.4230
0.2735	2.0	1246	0.2726	0.5221	0.2726	0.4093
0.272	3.0	1869	0.2732	0.5227	0.2732	0.4190
0.2699	4.0	2492	0.2737	0.5231	0.2737	0.4027
0.2682	5.0	3115	0.2783	0.5276	0.2783	0.4265
0.2665	6.0	3738	0.2746	0.5241	0.2746	0.4153

Framework versions

Transformers 4.19.0.dev0
Pytorch 1.9.0+cu111
Datasets 2.4.0
Tokenizers 0.12.1