nosql-identifier-roberta-base

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

• Loss: 0.8502
• Accuracy: 0.775

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	0.5647	0.825
No log	2.0	80	0.4160	0.75
No log	3.0	120	0.8697	0.75
No log	4.0	160	0.7257	0.775
No log	5.0	200	0.4974	0.875
No log	6.0	240	0.6685	0.85
No log	7.0	280	0.7686	0.85
No log	8.0	320	0.7531	0.875
No log	9.0	360	0.9639	0.8
No log	10.0	400	0.6153	0.9
No log	11.0	440	0.6570	0.875
No log	12.0	480	0.7417	0.825
0.2644	13.0	520	0.8697	0.825
0.2644	14.0	560	0.8611	0.8
0.2644	15.0	600	0.8502	0.775

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.11.0