TenaliAI-FinTech-v1

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

• Loss: 0.6760

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 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
1.7046	1.0	2163	1.3254
0.9319	2.0	4326	0.8316
0.748	3.0	6489	0.7299
0.6583	4.0	8652	0.6946
0.6182	5.0	10815	0.6901
0.5848	6.0	12978	0.6760
0.5789	7.0	15141	0.6797
0.543	8.0	17304	0.6948
0.5364	9.0	19467	0.7041
0.5203	10.0	21630	0.7032
0.4974	11.0	23793	0.7076
0.519	12.0	25956	0.7232
0.5235	13.0	28119	0.7073
0.5332	14.0	30282	0.7254
0.5109	15.0	32445	0.7158
0.5031	16.0	34608	0.7207
0.5169	17.0	36771	0.7369
0.4915	18.0	38934	0.7322
0.4975	19.0	41097	0.7422
0.4961	20.0	43260	0.7533
0.4692	21.0	45423	0.7670
0.5122	22.0	47586	0.7420
0.5024	23.0	49749	0.7388
0.4867	24.0	51912	0.7470
0.4884	25.0	54075	0.7474

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Tokenizers 0.20.3