Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: google/vivit-b-16x2-kinetics400
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: vvt-gs-rot-flip-wtoken-f198-4.4-h768-t8.16.16
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# vvt-gs-rot-flip-wtoken-f198-4.4-h768-t8.16.16
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.7411
|
| 21 |
+
- Accuracy: 0.6984
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- training_steps: 5500
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 53 |
+
| 1.0266 | 0.0402 | 221 | 1.0406 | 0.4286 |
|
| 54 |
+
| 1.0928 | 1.0402 | 442 | 0.9597 | 0.5291 |
|
| 55 |
+
| 0.862 | 2.0402 | 663 | 0.9646 | 0.4709 |
|
| 56 |
+
| 0.9291 | 3.0402 | 884 | 0.9939 | 0.4868 |
|
| 57 |
+
| 0.8705 | 4.0402 | 1105 | 1.0091 | 0.5503 |
|
| 58 |
+
| 0.9667 | 5.0402 | 1326 | 0.9416 | 0.5556 |
|
| 59 |
+
| 0.9227 | 6.0402 | 1547 | 0.8647 | 0.5820 |
|
| 60 |
+
| 1.0569 | 7.0402 | 1768 | 1.1076 | 0.4127 |
|
| 61 |
+
| 0.9919 | 8.0402 | 1989 | 0.9308 | 0.5608 |
|
| 62 |
+
| 0.7163 | 9.0402 | 2210 | 0.9721 | 0.5185 |
|
| 63 |
+
| 0.7941 | 10.0402 | 2431 | 0.9408 | 0.5397 |
|
| 64 |
+
| 0.9386 | 11.0402 | 2652 | 0.8730 | 0.5926 |
|
| 65 |
+
| 0.857 | 12.0402 | 2873 | 0.8833 | 0.6561 |
|
| 66 |
+
| 0.7059 | 13.0402 | 3094 | 0.8673 | 0.6402 |
|
| 67 |
+
| 0.8322 | 14.0402 | 3315 | 0.8233 | 0.6296 |
|
| 68 |
+
| 0.8574 | 15.0402 | 3536 | 0.7643 | 0.6825 |
|
| 69 |
+
| 0.7092 | 16.0402 | 3757 | 0.7972 | 0.6720 |
|
| 70 |
+
| 0.6816 | 17.0402 | 3978 | 0.7122 | 0.7090 |
|
| 71 |
+
| 0.839 | 18.0402 | 4199 | 0.7404 | 0.7143 |
|
| 72 |
+
| 0.4672 | 19.0402 | 4420 | 0.7093 | 0.7196 |
|
| 73 |
+
| 0.5119 | 20.0402 | 4641 | 0.7171 | 0.6825 |
|
| 74 |
+
| 0.7769 | 21.0402 | 4862 | 0.7072 | 0.6931 |
|
| 75 |
+
| 0.6635 | 22.0402 | 5083 | 0.7096 | 0.7196 |
|
| 76 |
+
| 0.8027 | 23.0402 | 5304 | 0.6887 | 0.7037 |
|
| 77 |
+
| 0.4765 | 24.0356 | 5500 | 0.6835 | 0.7407 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.41.2
|
| 83 |
+
- Pytorch 1.13.0+cu117
|
| 84 |
+
- Datasets 2.20.0
|
| 85 |
+
- Tokenizers 0.19.1
|