tradingview_signal_distilbert

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

• Loss: 0.0155
• F1: 0.9977
• Acc: 0.9977

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: 32
• eval_batch_size: 32
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Acc
0.7889	1.0	320	0.6306	0.7256	0.7370
0.5188	2.0	640	0.3389	0.8721	0.8717
0.3071	3.0	960	0.1820	0.9416	0.9414
0.1851	4.0	1280	0.1111	0.9666	0.9666
0.12	5.0	1600	0.0816	0.9731	0.9731
0.0777	6.0	1920	0.0528	0.9830	0.9830
0.0628	7.0	2240	0.0417	0.9906	0.9906
0.0443	8.0	2560	0.0490	0.9883	0.9883
0.038	9.0	2880	0.0562	0.9895	0.9895
0.0277	10.0	3200	0.0350	0.9941	0.9941
0.0179	11.0	3520	0.0214	0.9965	0.9965
0.022	12.0	3840	0.0189	0.9965	0.9965
0.0185	13.0	4160	0.0130	0.9977	0.9977
0.0123	14.0	4480	0.0116	0.9977	0.9977
0.0127	15.0	4800	0.0126	0.9982	0.9982
0.0095	16.0	5120	0.0160	0.9971	0.9971
0.0092	17.0	5440	0.0128	0.9982	0.9982
0.0109	18.0	5760	0.0181	0.9977	0.9977
0.0091	19.0	6080	0.0141	0.9977	0.9977
0.0067	20.0	6400	0.0155	0.9977	0.9977

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1