smish_fin

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

• Loss: 0.0658
• Accuracy: 0.9943

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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	Accuracy
No log	1.0	442	0.0621	0.9870
0.069	2.0	884	0.0490	0.9921
0.0133	3.0	1326	0.0429	0.9932
0.0045	4.0	1768	0.0585	0.9926
0.0011	5.0	2210	0.0591	0.9926
0.0015	6.0	2652	0.0644	0.9926
0.0001	7.0	3094	0.0665	0.9926
0.0001	8.0	3536	0.0695	0.9921
0.0001	9.0	3978	0.0807	0.9915
0.0001	10.0	4420	0.0602	0.9938
0.0047	11.0	4862	0.0831	0.9915
0.0013	12.0	5304	0.0719	0.9921
0.0028	13.0	5746	0.0592	0.9932
0.0002	14.0	6188	0.0622	0.9938
0.0	15.0	6630	0.0635	0.9943
0.0	16.0	7072	0.0646	0.9943
0.0	17.0	7514	0.0655	0.9943
0.0	18.0	7956	0.0664	0.9943
0.0	19.0	8398	0.0615	0.9943
0.0017	20.0	8840	0.0625	0.9943
0.0	21.0	9282	0.0634	0.9943
0.0	22.0	9724	0.0640	0.9943
0.0	23.0	10166	0.0653	0.9943
0.0	24.0	10608	0.0656	0.9943
0.0	25.0	11050	0.0658	0.9943

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0