README.md

metadata

library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - datasaur-dev/datasaur-MTFiZjUwM2Q-ZWJiZDRmNGI
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: autotrain-radesky-lab-span-v1
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: datasaur-dev/datasaur-MTFiZjUwM2Q-ZWJiZDRmNGI
          type: datasaur-dev/datasaur-MTFiZjUwM2Q-ZWJiZDRmNGI
          config: default
          split: validation
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.7853658536585366
          - name: Recall
            type: recall
            value: 0.8385416666666666
          - name: F1
            type: f1
            value: 0.8110831234256927
          - name: Accuracy
            type: accuracy
            value: 0.9709519365375642

autotrain-radesky-lab-span-v1

This model is a fine-tuned version of bert-base-uncased on the datasaur-dev/datasaur-MTFiZjUwM2Q-ZWJiZDRmNGI dataset. It achieves the following results on the evaluation set:

• Loss: 0.2518
• Precision: 0.7854
• Recall: 0.8385
• F1: 0.8111
• Accuracy: 0.9710

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	455	0.2565	0.5114	0.4688	0.4891	0.9440
0.2875	2.0	910	0.3292	0.2957	0.2865	0.2910	0.9238
0.1173	3.0	1365	0.1931	0.4347	0.7448	0.5489	0.9531
0.0945	4.0	1820	0.1780	0.5147	0.7292	0.6034	0.9578
0.0559	5.0	2275	0.1924	0.5496	0.75	0.6344	0.9592
0.0412	6.0	2730	0.1673	0.6637	0.7708	0.7133	0.9654
0.0309	7.0	3185	0.1928	0.64	0.75	0.6906	0.9635
0.0231	8.0	3640	0.1938	0.6332	0.7552	0.6888	0.9643
0.0191	9.0	4095	0.1856	0.6667	0.7812	0.7194	0.9670
0.018	10.0	4550	0.2042	0.6610	0.8125	0.7290	0.9659
0.0138	11.0	5005	0.2254	0.6245	0.7969	0.7002	0.9649
0.0138	12.0	5460	0.2193	0.7318	0.8385	0.7816	0.9693
0.0104	13.0	5915	0.2287	0.6568	0.8073	0.7243	0.9643
0.0088	14.0	6370	0.2258	0.6943	0.8281	0.7553	0.9683
0.0052	15.0	6825	0.2323	0.7537	0.7969	0.7747	0.9677
0.0091	16.0	7280	0.2226	0.7067	0.8281	0.7626	0.9678
0.0039	17.0	7735	0.2152	0.7393	0.8125	0.7742	0.9696
0.006	18.0	8190	0.2687	0.7340	0.7760	0.7544	0.9672
0.0024	19.0	8645	0.2464	0.7358	0.8125	0.7723	0.9690
0.0004	20.0	9100	0.2463	0.7583	0.8333	0.7940	0.9694
0.0003	21.0	9555	0.2466	0.7805	0.8333	0.8060	0.9700
0.001	22.0	10010	0.2514	0.7822	0.8229	0.8020	0.9706
0.001	23.0	10465	0.2518	0.7854	0.8385	0.8111	0.9710
0.0002	24.0	10920	0.2586	0.7833	0.8281	0.8051	0.9705
0.0002	25.0	11375	0.2650	0.7681	0.8281	0.7970	0.9697

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu124
• Datasets 2.20.0
• Tokenizers 0.21.0