Hugging Face's logo

beingbatman
/
CTMAE-P2-V4-S3

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
CTMAE-P2-V4-S3 / README.md
beingbatman's picture
beingbatman
Model save
dbf3f72 verified
preview code
|
raw
history blame contribute delete
4.65 kB
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: CTMAE-P2-V4-S3
    results: []

CTMAE-P2-V4-S3

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: 2.1094
  • Accuracy: 0.7111

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: 1
  • eval_batch_size: 1
  • 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: 13050

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.5461 0.02 261 2.1854 0.5556
0.6074 1.02 522 2.6518 0.5556
1.5766 2.02 783 1.9843 0.5556
0.7713 3.02 1044 2.2332 0.5556
1.797 4.02 1305 1.7064 0.5556
0.8914 5.02 1566 1.8977 0.5556
0.7372 6.02 1827 2.2072 0.5556
1.0467 7.02 2088 1.7544 0.5556
1.2248 8.02 2349 2.0315 0.5556
0.7126 9.02 2610 1.7717 0.5556
1.2486 10.02 2871 2.0448 0.5556
2.2836 11.02 3132 2.1988 0.5556
0.8409 12.02 3393 1.6258 0.6444
0.4642 13.02 3654 1.3451 0.6667
0.007 14.02 3915 2.2438 0.5556
0.9377 15.02 4176 1.1871 0.6444
0.7025 16.02 4437 1.8905 0.6444
0.2657 17.02 4698 2.1760 0.6222
1.3937 18.02 4959 2.0622 0.6
1.9924 19.02 5220 1.8416 0.6667
0.0009 20.02 5481 1.9068 0.6444
1.0231 21.02 5742 1.8428 0.6667
0.7099 22.02 6003 2.3108 0.6
0.3243 23.02 6264 2.2084 0.5778
2.748 24.02 6525 1.8855 0.6889
0.0002 25.02 6786 1.9443 0.6667
1.1288 26.02 7047 1.6372 0.6444
0.0024 27.02 7308 2.0813 0.6444
1.3731 28.02 7569 2.1846 0.6444
0.0085 29.02 7830 2.2414 0.6222
0.0004 30.02 8091 2.5363 0.5778
0.7817 31.02 8352 2.8433 0.5778
0.3487 32.02 8613 2.6374 0.6444
0.0014 33.02 8874 3.0313 0.5778
0.0009 34.02 9135 2.6187 0.6667
0.014 35.02 9396 2.1094 0.7111
0.512 36.02 9657 2.1110 0.6667
0.0003 37.02 9918 3.0441 0.5778
0.0001 38.02 10179 2.4423 0.6889
0.0009 39.02 10440 2.3538 0.6889
0.0001 40.02 10701 2.4812 0.6667
0.0001 41.02 10962 2.5847 0.6667
0.0 42.02 11223 2.5525 0.6889
0.002 43.02 11484 2.6746 0.6889
0.0004 44.02 11745 2.4888 0.6667
0.0001 45.02 12006 2.5662 0.6444
0.0011 46.02 12267 2.5288 0.6667
0.0001 47.02 12528 2.5611 0.6667
0.7043 48.02 12789 2.7606 0.6667
0.0001 49.02 13050 2.7966 0.6667

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.0.1+cu117
  • Datasets 3.0.1
  • Tokenizers 0.20.0