metadata

library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
datasets:
  - wnut_17
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: modernbert-base-wnut17-english-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: wnut_17
          type: wnut_17
          config: wnut_17
          split: test
          args: wnut_17
        metrics:
          - name: Precision
            type: precision
            value: 0.5518248175182482
          - name: Recall
            type: recall
            value: 0.35032437442076
          - name: F1
            type: f1
            value: 0.4285714285714286
          - name: Accuracy
            type: accuracy
            value: 0.9457125758741558

modernbert-base-wnut17-english-ner

This model is a fine-tuned version of answerdotai/ModernBERT-base on the wnut_17 dataset. It achieves the following results on the evaluation set:

Loss: 0.5510
Precision: 0.5518
Recall: 0.3503
F1: 0.4286
Accuracy: 0.9457

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: 32
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	107	0.3280	0.2601	0.0778	0.1198	0.9292
No log	2.0	214	0.2790	0.5609	0.2048	0.3001	0.9377
No log	3.0	321	0.2860	0.4403	0.2595	0.3265	0.9394
No log	4.0	428	0.3018	0.4534	0.3698	0.4074	0.9442
0.1707	5.0	535	0.3328	0.4742	0.3661	0.4132	0.9445
0.1707	6.0	642	0.4206	0.5119	0.3401	0.4087	0.9445
0.1707	7.0	749	0.4242	0.5238	0.3364	0.4097	0.9449
0.1707	8.0	856	0.4635	0.5624	0.3133	0.4024	0.9447
0.1707	9.0	963	0.4705	0.5432	0.3494	0.4253	0.9461
0.0052	10.0	1070	0.4557	0.4962	0.3652	0.4207	0.9456
0.0052	11.0	1177	0.5900	0.5956	0.3234	0.4192	0.9448
0.0052	12.0	1284	0.5206	0.5701	0.3429	0.4282	0.9456
0.0052	13.0	1391	0.5535	0.5805	0.3309	0.4215	0.9455
0.0052	14.0	1498	0.5098	0.5297	0.3559	0.4257	0.9457
0.0011	15.0	1605	0.5543	0.5681	0.3401	0.4255	0.9457
0.0011	16.0	1712	0.5394	0.5512	0.3494	0.4277	0.9456
0.0011	17.0	1819	0.5492	0.5577	0.3448	0.4261	0.9457
0.0011	18.0	1926	0.5412	0.5489	0.3540	0.4304	0.9458
0.0008	19.0	2033	0.5472	0.5485	0.3513	0.4282	0.9456
0.0008	20.0	2140	0.5510	0.5518	0.3503	0.4286	0.9457

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.21.0