README.md

metadata

library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: bert-seq-class-values-no-context_plus
    results: []

bert-seq-class-values-no-context_plus

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

• Loss: 0.3789
• Subset Accuracy: 0.2907
• F1 Macro: 0.3225
• F1 Micro: 0.3837
• Precision Macro: 0.3470
• Recall Macro: 0.3052
• Roc Auc: 0.7784

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: 16
• eval_batch_size: 16
• seed: 2025
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Subset Accuracy	F1 Macro	F1 Micro	Precision Macro	Recall Macro	Roc Auc
0.3261	1.0	767	0.1848	0.0358	0.0273	0.0682	0.1322	0.0165	0.7523
0.1653	2.0	1534	0.1687	0.2000	0.1740	0.3048	0.3058	0.1429	0.8180
0.1422	3.0	2301	0.1700	0.2427	0.2509	0.3398	0.4408	0.1957	0.8239
0.1091	4.0	3068	0.1864	0.3055	0.2801	0.3921	0.4249	0.2469	0.8166
0.0806	5.0	3835	0.2045	0.3021	0.2926	0.3841	0.3993	0.2540	0.8079
0.0542	6.0	4602	0.2328	0.2992	0.2961	0.3785	0.3630	0.2644	0.7991
0.0434	7.0	5369	0.2475	0.2842	0.3076	0.3845	0.3510	0.2955	0.7982
0.0311	8.0	6136	0.2661	0.2919	0.3236	0.3904	0.3442	0.3168	0.7920
0.025	9.0	6903	0.2812	0.2844	0.3201	0.3858	0.3441	0.3085	0.7878
0.0186	10.0	7670	0.3123	0.2826	0.3246	0.3879	0.3432	0.3220	0.7827
0.0152	11.0	8437	0.3156	0.2689	0.3217	0.3774	0.3374	0.3157	0.7828
0.0109	12.0	9204	0.3380	0.2856	0.3127	0.3800	0.3410	0.2994	0.7785
0.0095	13.0	9971	0.3636	0.2684	0.3187	0.3783	0.3385	0.3140	0.7699
0.0063	14.0	10738	0.3684	0.2835	0.3206	0.3807	0.3478	0.3049	0.7755
0.0054	15.0	11505	0.3789	0.2907	0.3225	0.3837	0.3470	0.3052	0.7784

Framework versions

• Transformers 4.53.2
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.2