Downloads · 30 days
4
6% of all-time downloads
AV_MAE_DF1M_noCE_new
yadvender12/AV_MAE_DF1M_noCE_new
AV_MAE_DF1M_noCE_new is a video classification model from yadvender12. Use it for the video classification task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
62
Public
Parameters
172M
4.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors690 MB · 100%
At a glance
- Task
- Video Classification
- Library
- transformers
- Model type
- videomae
- Access
- Public
- Created
- May 16, 2024
- Updated
- May 16, 2024
- SHA
- 9a89de27
Model card
From the Hugging Face model README
<!-- 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. -->
AV_MAE_DF1M_noCE_new
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2999
- Accuracy: 0.9371
- F1: 0.9367
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 28240
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4126 | 0.16 | 4517 | 0.4441 | 0.8969 | 0.8954 |
| 0.3429 | 1.16 | 9033 | 0.3442 | 0.9153 | 0.9151 |
| 0.9624 | 2.16 | 13549 | 0.3376 | 0.9225 | 0.9223 |
| 0.408 | 3.16 | 18066 | 0.3046 | 0.9302 | 0.9300 |
| 0.1189 | 4.16 | 22582 | 0.3120 | 0.9357 | 0.9354 |
| 0.2586 | 5.16 | 27099 | 0.3090 | 0.9355 | 0.9350 |
| 0.3502 | 6.04 | 28240 | 0.2999 | 0.9371 | 0.9367 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.1
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- Created
- May 16, 2024
- Updated
- May 16, 2024