distilbert-base-uncased-issues-128-FINER-ABSA

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

• Loss: 2.2755

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: 8
• 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: 40

Training results

Training Loss	Epoch	Step	Validation Loss
2.3368	1.0	388	2.1709
2.0795	2.0	776	2.4556
1.9588	3.0	1164	2.1362
1.8588	4.0	1552	2.1211
1.7829	5.0	1940	2.0847
1.7205	6.0	2328	1.9679
1.6457	7.0	2716	2.3018
1.592	8.0	3104	2.5476
1.5514	9.0	3492	2.1689
1.4995	10.0	3880	2.3121
1.454	11.0	4268	2.0584
1.4353	12.0	4656	2.4454
1.398	13.0	5044	2.3003
1.3632	14.0	5432	2.2741
1.3431	15.0	5820	2.3972
1.2959	16.0	6208	2.0092
1.2502	17.0	6596	2.6074
1.2428	18.0	6984	2.4610
1.2173	19.0	7372	2.2601
1.1897	20.0	7760	1.9136
1.1794	21.0	8148	2.3777
1.1414	22.0	8536	2.4453
1.1451	23.0	8924	2.2062
1.0995	24.0	9312	2.0046
1.0842	25.0	9700	2.3008
1.0775	26.0	10088	2.2165
1.0534	27.0	10476	2.4383
1.045	28.0	10864	2.5337
1.0316	29.0	11252	1.9797
1.0143	30.0	11640	2.3651
0.9912	31.0	12028	2.2892
0.9995	32.0	12416	2.2585
0.9715	33.0	12804	2.3780
0.9683	34.0	13192	2.1615
0.9452	35.0	13580	2.5597
0.9563	36.0	13968	2.3249
0.9555	37.0	14356	2.6080
0.9446	38.0	14744	2.2567
0.9307	39.0	15132	2.3204
0.9306	40.0	15520	2.2755

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1