Roberta_Text_Classification_v6

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

• Loss: 0.0230

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-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
• lr_scheduler_warmup_steps: 500
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
0.023	1.0	279	0.2139
0.0967	2.0	558	0.0710
0.0004	3.0	837	0.0981
0.1198	4.0	1116	0.0474
0.1475	5.0	1395	0.1094
0.0008	6.0	1674	0.0379
0.2435	7.0	1953	0.0536
0.0001	8.0	2232	0.0765
0.0002	9.0	2511	0.0483
0.0002	10.0	2790	0.0406
0.0001	11.0	3069	0.0430
0.0001	12.0	3348	0.0399
0.0002	13.0	3627	0.0230
0.0002	14.0	3906	0.0353
0.0671	15.0	4185	0.0724
0.0154	16.0	4464	0.1768
0.0002	17.0	4743	0.0470
0.0001	18.0	5022	0.0451
0.2172	19.0	5301	0.0504
0.0128	20.0	5580	0.0676
0.0001	21.0	5859	0.1007
0.0001	22.0	6138	0.0799
0.0001	23.0	6417	0.0616
0.0	24.0	6696	0.0621
0.0	25.0	6975	0.0625
0.0	26.0	7254	0.0628
0.0	27.0	7533	0.0631
0.0	28.0	7812	0.0633
0.0	29.0	8091	0.0637
0.0	30.0	8370	0.0638

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1