bert-bias-classifier_teacher

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

• Loss: 0.0000
• Accuracy: 1.0
• Auc: 1.0

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: 0.0002
• train_batch_size: 20
• eval_batch_size: 20
• 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: 80

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc
0.0312	1.0	1600	0.0007	1.0	1.0
0.0093	2.0	3200	0.0023	0.999	1.0
0.0088	3.0	4800	0.0010	1.0	1.0
0.0061	4.0	6400	0.0002	1.0	1.0
0.0075	5.0	8000	0.0000	1.0	1.0
0.0052	6.0	9600	0.0001	1.0	1.0
0.0059	7.0	11200	0.0055	0.998	1.0
0.0048	8.0	12800	0.0048	0.998	1.0
0.0034	9.0	14400	0.0000	1.0	1.0
0.004	10.0	16000	0.0001	1.0	1.0
0.0043	11.0	17600	0.0001	1.0	1.0
0.0037	12.0	19200	0.0000	1.0	1.0
0.0032	13.0	20800	0.0000	1.0	1.0
0.0033	14.0	22400	0.0001	1.0	1.0
0.0028	15.0	24000	0.0003	1.0	1.0
0.0032	16.0	25600	0.0000	1.0	1.0
0.0021	17.0	27200	0.0000	1.0	1.0
0.002	18.0	28800	0.0001	1.0	1.0
0.0019	19.0	30400	0.0014	1.0	1.0
0.0021	20.0	32000	0.0000	1.0	1.0
0.0014	21.0	33600	0.0000	1.0	1.0
0.0018	22.0	35200	0.0001	1.0	1.0
0.0025	23.0	36800	0.0001	1.0	1.0
0.0021	24.0	38400	0.0000	1.0	1.0
0.0015	25.0	40000	0.0000	1.0	1.0
0.0018	26.0	41600	0.0000	1.0	1.0
0.0016	27.0	43200	0.0000	1.0	1.0
0.0016	28.0	44800	0.0000	1.0	1.0
0.002	29.0	46400	0.0000	1.0	1.0
0.002	30.0	48000	0.0000	1.0	1.0
0.0014	31.0	49600	0.0000	1.0	1.0
0.0021	32.0	51200	0.0000	1.0	1.0
0.0016	33.0	52800	0.0000	1.0	1.0
0.0018	34.0	54400	0.0000	1.0	1.0
0.0012	35.0	56000	0.0004	1.0	1.0
0.0014	36.0	57600	0.0000	1.0	1.0
0.0014	37.0	59200	0.0000	1.0	1.0
0.0016	38.0	60800	0.0002	1.0	1.0
0.0015	39.0	62400	0.0000	1.0	1.0
0.0008	40.0	64000	0.0000	1.0	1.0
0.0008	41.0	65600	0.0001	1.0	1.0
0.0011	42.0	67200	0.0000	1.0	1.0
0.0011	43.0	68800	0.0000	1.0	1.0
0.0015	44.0	70400	0.0000	1.0	1.0
0.0011	45.0	72000	0.0000	1.0	1.0
0.0009	46.0	73600	0.0000	1.0	1.0
0.0006	47.0	75200	0.0000	1.0	1.0
0.0011	48.0	76800	0.0000	1.0	1.0
0.0015	49.0	78400	0.0001	1.0	1.0
0.0009	50.0	80000	0.0000	1.0	1.0
0.0012	51.0	81600	0.0000	1.0	1.0
0.0005	52.0	83200	0.0001	1.0	1.0
0.0008	53.0	84800	0.0000	1.0	1.0
0.0009	54.0	86400	0.0010	1.0	1.0
0.0006	55.0	88000	0.0002	1.0	1.0
0.0008	56.0	89600	0.0000	1.0	1.0
0.0008	57.0	91200	0.0000	1.0	1.0
0.0009	58.0	92800	0.0000	1.0	1.0
0.0005	59.0	94400	0.0000	1.0	1.0
0.0008	60.0	96000	0.0000	1.0	1.0
0.0004	61.0	97600	0.0000	1.0	1.0
0.0006	62.0	99200	0.0000	1.0	1.0
0.0005	63.0	100800	0.0000	1.0	1.0
0.0007	64.0	102400	0.0000	1.0	1.0
0.0005	65.0	104000	0.0000	1.0	1.0
0.0009	66.0	105600	0.0000	1.0	1.0
0.0009	67.0	107200	0.0000	1.0	1.0
0.0006	68.0	108800	0.0000	1.0	1.0
0.0003	69.0	110400	0.0000	1.0	1.0
0.0008	70.0	112000	0.0000	1.0	1.0
0.0005	71.0	113600	0.0000	1.0	1.0
0.0003	72.0	115200	0.0000	1.0	1.0
0.0005	73.0	116800	0.0000	1.0	1.0
0.0006	74.0	118400	0.0000	1.0	1.0
0.0003	75.0	120000	0.0000	1.0	1.0
0.0008	76.0	121600	0.0000	1.0	1.0
0.0004	77.0	123200	0.0000	1.0	1.0
0.0007	78.0	124800	0.0000	1.0	1.0
0.0005	79.0	126400	0.0000	1.0	1.0
0.0005	80.0	128000	0.0000	1.0	1.0

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.1
• Datasets 3.6.0
• Tokenizers 0.21.1