ctsinov1 / README.md
beingbatman's picture
Model save
553755a verified
metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-large-finetuned-kinetics
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ctsinov1
    results: []

ctsinov1

This model is a fine-tuned version of MCG-NJU/videomae-large-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7987
  • Accuracy: 0.8586

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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 17500

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5787 0.02 350 0.5787 0.7104
0.5175 1.02 700 0.7402 0.8081
0.4062 2.02 1050 0.8532 0.8283
0.7962 3.02 1400 0.7184 0.8114
0.8225 4.02 1750 1.6868 0.5657
0.724 5.02 2100 1.0066 0.7508
0.1468 6.02 2450 0.7703 0.8316
0.8406 7.02 2800 0.5863 0.8485
0.4485 8.02 3150 0.6602 0.8384
0.0134 9.02 3500 0.6907 0.8316
0.11 10.02 3850 0.7098 0.8316
0.6557 11.02 4200 0.6507 0.8384
0.2642 12.02 4550 0.6555 0.8519
0.2413 13.02 4900 0.6481 0.8519
0.6278 14.02 5250 0.6555 0.8552
0.0107 15.02 5600 0.6550 0.8519
0.3013 16.02 5950 0.7405 0.8485
0.5055 17.02 6300 0.6563 0.8451
0.0059 18.02 6650 0.6917 0.8485
0.4332 19.02 7000 0.6888 0.8384
0.2602 20.02 7350 0.7993 0.8418
0.2142 21.02 7700 0.7131 0.8451
0.5742 22.02 8050 0.9735 0.7980
0.2504 23.02 8400 0.8314 0.8384
0.8514 24.02 8750 0.7481 0.8418
0.8148 25.02 9100 0.7210 0.8384
0.2594 26.02 9450 0.9980 0.8249
0.6742 27.02 9800 0.7987 0.8586
0.0063 28.02 10150 0.9369 0.8316
0.5186 29.02 10500 1.0871 0.8148
0.3076 30.02 10850 0.8931 0.8350
0.1113 31.02 11200 1.0014 0.8384
0.2201 32.02 11550 0.8628 0.8485
0.0324 33.02 11900 0.9972 0.8350
0.4411 34.02 12250 1.0592 0.8350
0.0011 35.02 12600 1.0746 0.8283
0.3917 36.02 12950 0.9696 0.8384
0.7268 37.02 13300 1.1062 0.8182
0.3747 38.02 13650 1.0368 0.8350
0.5584 39.02 14000 1.0149 0.8418
0.4637 40.02 14350 1.0104 0.8316
0.0014 41.02 14700 1.0437 0.8418
0.6253 42.02 15050 1.1687 0.8148
0.0009 43.02 15400 1.0243 0.8418
0.0003 44.02 15750 1.0864 0.8316
0.291 45.02 16100 1.0647 0.8384
0.4962 46.02 16450 1.1166 0.8316
0.0919 47.02 16800 1.1209 0.8283
0.0007 48.02 17150 1.1260 0.8316
0.0008 49.02 17500 1.1139 0.8350

Framework versions

  • Transformers 4.56.2
  • Pytorch 2.6.0+cu118
  • Datasets 2.2.1
  • Tokenizers 0.22.1