Timesformer Wlasl 100 200ep CoR
This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 2.5784 Accuracy: 0.5592
Model source
- Kind
- Other
- File size
- 463 MB
- Base model
- facebook/timesformer-base-finetuned-k400
- Version
- vModel
- Updated
- Oct 24, 2026
- Source
- Hugging Face
Source description
timesformer_wlasl_100_200ep_coR_
This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5784
- Accuracy: 0.5592
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 |
|---|---|---|---|---|
| 18.9003 | 0.005 | 180 | 4.6868 | 0.0089 |
| 18.3693 | 1.0050 | 360 | 4.5353 | 0.0414 |
| 17.2476 | 2.0050 | 540 | 4.2835 | 0.0828 |
| 15.3051 | 3.0050 | 721 | 3.8992 | 0.1598 |
| 12.9592 | 4.005 | 901 | 3.4829 | 0.2456 |
| 10.4934 | 5.0050 | 1081 | 3.1537 | 0.3491 |
| 8.2588 | 6.0050 | 1261 | 2.8115 | 0.4172 |
| 6.1765 | 7.0050 | 1442 | 2.5671 | 0.4438 |
| 4.321 | 8.005 | 1622 | 2.2792 | 0.5030 |
| 2.874 | 9.0050 | 1802 | 2.1045 | 0.5296 |
| 1.7634 | 10.0050 | 1982 | 1.9738 | 0.5414 |
| 1.0891 | 11.0050 | 2163 | 1.8931 | 0.5592 |
| 0.6992 | 12.005 | 2343 | 1.7606 | 0.5651 |
| 0.429 | 13.0050 | 2523 | 1.6879 | 0.5799 |
| 0.327 | 14.0050 | 2703 | 1.7075 | 0.5976 |
| 0.1959 | 15.0050 | 2884 | 1.6486 | 0.5917 |
| 0.1588 | 16.005 | 3064 | 1.8440 | 0.5621 |
| 0.1563 | 17.0050 | 3244 | 1.7394 | 0.5888 |
| 0.1913 | 18.0050 | 3424 | 1.9017 | 0.5710 |
| 0.1603 | 19.0050 | 3605 | 1.9527 | 0.5828 |
| 0.1007 | 20.005 | 3785 | 1.9093 | 0.6124 |
| 0.0952 | 21.0050 | 3965 | 1.8047 | 0.6036 |
| 0.0833 | 22.0050 | 4145 | 1.9631 | 0.5680 |
| 0.1537 | 23.0050 | 4326 | 1.9207 | 0.6154 |
| 0.2198 | 24.005 | 4506 | 1.8979 | 0.5976 |
| 0.1316 | 25.0050 | 4686 | 1.9179 | 0.5917 |
| 0.1503 | 26.0050 | 4866 | 1.9743 | 0.5769 |
| 0.1429 | 27.0050 | 5047 | 2.0455 | 0.5740 |
| 0.0988 | 28.005 | 5227 | 2.0844 | 0.5710 |
| 0.1819 | 29.0050 | 5407 | 2.0516 | 0.5947 |
| 0.1184 | 30.0050 | 5587 | 2.4084 | 0.5621 |
| 0.1113 | 31.0050 | 5768 | 2.2745 | 0.5473 |
| 0.1382 | 32.005 | 5948 | 2.5505 | 0.5385 |
| 0.1375 | 33.0050 | 6128 | 2.2980 | 0.5592 |
| 0.2414 | 34.0050 | 6308 | 2.3081 | 0.5325 |
| 0.1255 | 35.0050 | 6489 | 2.1351 | 0.5858 |
| 0.1024 | 36.005 | 6669 | 2.1904 | 0.6006 |
| 0.1639 | 37.0050 | 6849 | 2.2539 | 0.5740 |
| 0.1625 | 38.0050 | 7029 | 2.1330 | 0.5858 |
| 0.2216 | 39.0050 | 7210 | 2.4128 | 0.5503 |
| 0.1648 | 40.005 | 7390 | 2.4292 | 0.5680 |
| 0.1276 | 41.0050 | 7570 | 2.3737 | 0.6036 |
| 0.0872 | 42.0050 | 7750 | 2.2201 | 0.6183 |
| 0.1366 | 43.0050 | 7931 | 2.3584 | 0.5917 |
| 0.0697 | 44.005 | 8111 | 2.2536 | 0.5858 |
| 0.109 | 45.0050 | 8291 | 2.1399 | 0.6095 |
| 0.1114 | 46.0050 | 8471 | 2.2859 | 0.5740 |
| 0.1043 | 47.0050 | 8652 | 2.4237 | 0.5592 |
| 0.0999 | 48.005 | 8832 | 2.4805 | 0.5385 |
| 0.2184 | 49.0050 | 9012 | 2.3002 | 0.5740 |
| 0.1776 | 50.0050 | 9192 | 2.3414 | 0.5533 |
| 0.1222 | 51.0050 | 9373 | 2.3839 | 0.5888 |
| 0.0687 | 52.005 | 9553 | 2.5990 | 0.5592 |
| 0.086 | 53.0050 | 9733 | 2.6002 | 0.5799 |
| 0.0403 | 54.0050 | 9913 | 2.3152 | 0.5947 |
| 0.0603 | 55.0050 | 10094 | 2.4402 | 0.5858 |
| 0.044 | 56.005 | 10274 | 2.3451 | 0.6124 |
| 0.1193 | 57.0050 | 10454 | 2.5141 | 0.5680 |
| 0.1068 | 58.0050 | 10634 | 2.6438 | 0.5828 |
| 0.0725 | 59.0050 | 10815 | 2.5138 | 0.5858 |
| 0.119 | 60.005 | 10995 | 2.5138 | 0.5888 |
| 0.1927 | 61.0050 | 11175 | 2.7776 | 0.5503 |
| 0.1458 | 62.0050 | 11355 | 2.5784 | 0.5592 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.1
Sources
1 source
Sources
1 sourceVerified Oct 24
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
2 excerpts
Source excerpts
2 excerpts--- library_name: transformers license: cc-by-nc-4.0 base_model: facebook/timesformer-base-finetuned-k400 tags: - generated_from_trainer metrics: - accuracy model-index: - name: timesformer_wlasl_100_200ep_coR_ 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. --> # timesformer_wlasl_100_200ep_coR_ This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.5784 - Accuracy: 0.5592 ## 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 | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 18.9003 | 0.005 | 180 | 4.6868 | 0.0089 | | 18.3693 | 1.0050 | 360 | 4.5353 | 0.0414 | | 17.2476 | 2.0050 | 540 | 4.2835 | 0.0828 | | 15.3051 | 3.0050 | 721 | 3.8992 | 0.1598 | | 12.9592 | 4.005 | 901 | 3.4829 | 0.2456 | | 10.4934 | 5.0050 | 1081 | 3.1537 | 0.3491 | | 8.2588 | 6.0050 | 1261 | 2.8115 | 0.4172 | | 6.1765 | 7.0050 | 1442 | 2.5671 | 0.4438 | | 4.321 | 8.005 | 1622 | 2.2792 | 0.5030 | | 2.874 | 9.0050 | 1802 | 2.1045 | 0.5296 | | 1.7634 | 10.0050 | 1982 | 1.9738 | 0.5414 | | 1.0891 | 11.0050 | 2163 | 1.8931 | 0.5592 | | 0.6992 | 12.005 | 2343 | 1.7606 | 0.5651 | | 0.429 | 13.0050 | 2523 | 1.6879 | 0.5799 | | 0.327 | 14.0050 | 2703 | 1.7075 | 0.5976 | | 0.1959 | 15.0050 | 2884 | 1.6486 | 0.5917 | | 0.1588 | 16.005 | 3064 | 1.8440 | 0.5621 | | 0.1563 | 17.0050 | 3244 | 1.7394 | 0.5888 | | 0.1913 | 18.0050 | 3424 | 1.9017 | 0.5710 | | 0.1603 | 19.0050 |...
Source context: 8 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/timesformer_wlasl_100_200ep_coR_
