noise_test_v1_no_model

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

• Loss: 0.2665
• Accuracy Offensive: 0.9267
• F1 Offensive: 0.9245
• Accuracy Targeted: 0.9324
• F1 Targeted: 0.9102
• Accuracy Stance: 0.8776
• F1 Stance: 0.8339

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Offensive	Accuracy Targeted	F1 Targeted	Accuracy Stance	F1 Stance
0.7441	1.0	1324	0.6579	0.8097	0.7856	0.6545	0.5178	0.7009	0.5777
0.5043	2.0	2648	0.3977	0.8920	0.8862	0.9252	0.9031	0.8769	0.8310
0.4323	3.0	3972	0.3412	0.8984	0.8934	0.9271	0.9050	0.8773	0.8326
0.3849	4.0	5296	0.3199	0.9052	0.9010	0.9313	0.9091	0.8746	0.8312
0.3679	5.0	6620	0.3025	0.9124	0.9088	0.9298	0.9075	0.8731	0.8299
0.3667	6.0	7944	0.2990	0.9169	0.9138	0.9313	0.9091	0.8773	0.8336
0.3557	7.0	9268	0.2924	0.9177	0.9147	0.9301	0.9079	0.8754	0.8316
0.3384	8.0	10592	0.2854	0.9230	0.9206	0.9305	0.9083	0.8754	0.8326
0.3293	9.0	11916	0.2838	0.9252	0.9229	0.9282	0.9061	0.8776	0.8335
0.3251	10.0	13240	0.2759	0.9260	0.9236	0.9320	0.9098	0.8769	0.8335
0.3153	11.0	14564	0.2676	0.9294	0.9273	0.9305	0.9083	0.8758	0.8327
0.3267	12.0	15888	0.2619	0.9309	0.9289	0.9335	0.9114	0.8826	0.8388
0.3093	13.0	17212	0.2713	0.9256	0.9234	0.9316	0.9094	0.8761	0.8326
0.3115	14.0	18536	0.2655	0.9286	0.9266	0.9298	0.9076	0.8735	0.8304

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.0.1
• Tokenizers 0.21.1