Petr Jaroch
DotCheck/Dotengine_v1.1
61b9b17 verified
|
Raw
History Blame Contribute Delete
2.36 kB
metadata
library_name: transformers
license: apache-2.0
base_model: DotCheck/finetuned_model
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: finetuned_video_model
    results: []

finetuned_video_model

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

  • Loss: 0.0674
  • Accuracy: 0.9821

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: 1e-05
  • train_batch_size: 512
  • eval_batch_size: 512
  • 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: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 14 0.1526 0.9615
No log 2.0 28 0.1366 0.9615
No log 3.0 42 0.1200 0.9654
No log 4.0 56 0.1034 0.9679
No log 5.0 70 0.0903 0.9692
No log 6.0 84 0.0833 0.9692
No log 7.0 98 0.0764 0.9782
No log 8.0 112 0.0745 0.9782
No log 9.0 126 0.0705 0.9808
No log 10.0 140 0.0706 0.9821
No log 11.0 154 0.0678 0.9821
No log 12.0 168 0.0678 0.9821
No log 13.0 182 0.0669 0.9833
No log 14.0 196 0.0677 0.9821
No log 15.0 210 0.0674 0.9821

Framework versions

  • Transformers 4.54.1
  • Pytorch 2.6.0+cu124
  • Datasets 4.0.0
  • Tokenizers 0.21.4