my_awesome_wnut_model

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

• Loss: 0.4684
• Precision: 0.4865
• Recall: 0.3494
• F1: 0.4067
• Accuracy: 0.9440

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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	Precision	Recall	F1	Accuracy
No log	1.0	213	0.2863	0.5189	0.3179	0.3943	0.9427
No log	2.0	426	0.3160	0.4378	0.3133	0.3652	0.9418
0.0602	3.0	639	0.3395	0.5007	0.3160	0.3875	0.9422
0.0602	4.0	852	0.3650	0.5213	0.3624	0.4276	0.9443
0.0231	5.0	1065	0.3833	0.5	0.3466	0.4094	0.9434
0.0231	6.0	1278	0.3958	0.5056	0.3327	0.4013	0.9438
0.0231	7.0	1491	0.3766	0.4452	0.3800	0.41	0.9433
0.0098	8.0	1704	0.3944	0.4573	0.3624	0.4043	0.9434
0.0098	9.0	1917	0.4326	0.4897	0.3318	0.3956	0.9434
0.0047	10.0	2130	0.4203	0.4764	0.3457	0.4006	0.9437
0.0047	11.0	2343	0.4555	0.5243	0.3401	0.4126	0.9444
0.0031	12.0	2556	0.4200	0.4840	0.3642	0.4157	0.9441
0.0031	13.0	2769	0.4481	0.5014	0.3401	0.4053	0.9442
0.0031	14.0	2982	0.4410	0.4806	0.3550	0.4083	0.9438
0.0025	15.0	3195	0.4548	0.4862	0.3429	0.4022	0.9435
0.0025	16.0	3408	0.5038	0.5223	0.3151	0.3931	0.9432
0.0017	17.0	3621	0.4635	0.4668	0.3448	0.3966	0.9431
0.0017	18.0	3834	0.4699	0.4823	0.3401	0.3989	0.9439
0.0015	19.0	4047	0.4646	0.4815	0.3503	0.4056	0.9437
0.0015	20.0	4260	0.4684	0.4865	0.3494	0.4067	0.9440

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0