TenaliAI-FinTech-v1 / README.md
credentek's picture
End of training
baba3b3 verified
metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: TenaliAI-FinTech-v1
    results: []

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: 0.7505

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 25

Training results

Training Loss Epoch Step Validation Loss
1.6215 1.0 5485 1.3611
0.9667 2.0 10970 0.9202
0.7911 3.0 16455 0.8125
0.7406 4.0 21940 0.7648
0.6934 5.0 27425 0.7711
0.6457 6.0 32910 0.7546
0.6511 7.0 38395 0.7506
0.6244 8.0 43880 0.7548
0.6076 9.0 49365 0.7505
0.6003 10.0 54850 0.7579
0.5649 11.0 60335 0.7583
0.5616 12.0 65820 0.7597
0.5688 13.0 71305 0.7685
0.5571 14.0 76790 0.7705
0.5709 15.0 82275 0.7666
0.56 16.0 87760 0.7790
0.5474 17.0 93245 0.7798
0.5431 18.0 98730 0.7906
0.541 19.0 104215 0.7987
0.5426 20.0 109700 0.7953
0.5534 21.0 115185 0.7978
0.5541 22.0 120670 0.7929
0.538 23.0 126155 0.7997
0.5463 24.0 131640 0.8205
0.5606 25.0 137125 0.8226

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1