| | --- |
| | library_name: transformers |
| | license: cc-by-nc-4.0 |
| | base_model: MCG-NJU/videomae-base |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: VideoMAE_Base_wlasl_100_longtail_200 |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # VideoMAE_Base_wlasl_100_longtail_200 |
| | |
| | This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 2.9736 |
| | - Accuracy: 0.4822 |
| | |
| | ## 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: 5e-05 |
| | - train_batch_size: 2 |
| | - eval_batch_size: 2 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 4 |
| | - total_train_batch_size: 8 |
| | - 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: 36000 |
| | - mixed_precision_training: Native AMP |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| | |:-------------:|:-------:|:----:|:---------------:|:--------:| |
| | | 18.7021 | 0.005 | 180 | 4.6442 | 0.0118 | |
| | | 18.6026 | 1.0050 | 360 | 4.6319 | 0.0118 | |
| | | 18.5393 | 2.0050 | 540 | 4.6238 | 0.0178 | |
| | | 18.3789 | 3.0050 | 721 | 4.6170 | 0.0178 | |
| | | 18.3763 | 4.005 | 901 | 4.6237 | 0.0178 | |
| | | 18.334 | 5.0050 | 1081 | 4.6342 | 0.0296 | |
| | | 18.1779 | 6.0050 | 1261 | 4.6036 | 0.0296 | |
| | | 17.9948 | 7.0050 | 1442 | 4.5903 | 0.0266 | |
| | | 17.9333 | 8.005 | 1622 | 4.6144 | 0.0237 | |
| | | 17.7505 | 9.0050 | 1802 | 4.5865 | 0.0118 | |
| | | 17.4917 | 10.0050 | 1982 | 4.5626 | 0.0207 | |
| | | 16.9821 | 11.0050 | 2163 | 4.3615 | 0.0444 | |
| | | 16.2362 | 12.005 | 2343 | 4.1515 | 0.0533 | |
| | | 15.2255 | 13.0050 | 2523 | 3.9603 | 0.0740 | |
| | | 14.0646 | 14.0050 | 2703 | 3.7594 | 0.0828 | |
| | | 12.8642 | 15.0050 | 2884 | 3.4154 | 0.1420 | |
| | | 11.6502 | 16.005 | 3064 | 3.3917 | 0.1627 | |
| | | 10.332 | 17.0050 | 3244 | 3.0359 | 0.2249 | |
| | | 8.9465 | 18.0050 | 3424 | 2.8625 | 0.2840 | |
| | | 7.6629 | 19.0050 | 3605 | 2.8202 | 0.3107 | |
| | | 6.2517 | 20.005 | 3785 | 2.6478 | 0.3343 | |
| | | 5.1876 | 21.0050 | 3965 | 2.4982 | 0.3728 | |
| | | 4.0929 | 22.0050 | 4145 | 2.3891 | 0.3876 | |
| | | 3.0425 | 23.0050 | 4326 | 2.2212 | 0.4083 | |
| | | 2.3667 | 24.005 | 4506 | 2.1609 | 0.4586 | |
| | | 1.7821 | 25.0050 | 4686 | 2.2471 | 0.4260 | |
| | | 1.4215 | 26.0050 | 4866 | 2.2263 | 0.4675 | |
| | | 1.1324 | 27.0050 | 5047 | 2.2360 | 0.4556 | |
| | | 0.9114 | 28.005 | 5227 | 2.2021 | 0.4852 | |
| | | 0.6966 | 29.0050 | 5407 | 2.3123 | 0.4408 | |
| | | 0.5676 | 30.0050 | 5587 | 2.1198 | 0.5355 | |
| | | 0.4494 | 31.0050 | 5768 | 2.2495 | 0.4911 | |
| | | 0.3321 | 32.005 | 5948 | 2.2658 | 0.5089 | |
| | | 0.227 | 33.0050 | 6128 | 2.4423 | 0.4882 | |
| | | 0.2203 | 34.0050 | 6308 | 2.4358 | 0.4763 | |
| | | 0.2643 | 35.0050 | 6489 | 2.5521 | 0.4675 | |
| | | 0.111 | 36.005 | 6669 | 2.5787 | 0.4882 | |
| | | 0.1009 | 37.0050 | 6849 | 2.4022 | 0.5059 | |
| | | 0.1275 | 38.0050 | 7029 | 2.5451 | 0.5 | |
| | | 0.1874 | 39.0050 | 7210 | 2.8339 | 0.4586 | |
| | | 0.1695 | 40.005 | 7390 | 3.0320 | 0.4320 | |
| | | 0.1735 | 41.0050 | 7570 | 2.6961 | 0.4941 | |
| | | 0.1299 | 42.0050 | 7750 | 2.9589 | 0.4675 | |
| | | 0.1399 | 43.0050 | 7931 | 2.6799 | 0.5325 | |
| | | 0.118 | 44.005 | 8111 | 2.8731 | 0.5 | |
| | | 0.1583 | 45.0050 | 8291 | 2.8757 | 0.4970 | |
| | | 0.1667 | 46.0050 | 8471 | 2.9294 | 0.4941 | |
| | | 0.202 | 47.0050 | 8652 | 3.1443 | 0.4615 | |
| | | 0.1301 | 48.005 | 8832 | 2.8941 | 0.5207 | |
| | | 0.2298 | 49.0050 | 9012 | 3.1270 | 0.4704 | |
| | | 0.1858 | 50.0050 | 9192 | 2.9736 | 0.4822 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.46.1 |
| | - Pytorch 2.5.1+cu124 |
| | - Datasets 3.1.0 |
| | - Tokenizers 0.20.1 |
| | |
