update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: videomae-base-finetuned-basketball-subset-v3-25epoch
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# videomae-base-finetuned-basketball-subset-v3-25epoch
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.8922
|
| 20 |
+
- Accuracy: 0.9
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
+
- training_steps: 5100
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 1.2489 | 0.04 | 202 | 0.7252 | 0.7 |
|
| 53 |
+
| 0.5366 | 1.04 | 404 | 1.2745 | 0.6 |
|
| 54 |
+
| 0.9659 | 2.04 | 606 | 0.7013 | 0.85 |
|
| 55 |
+
| 0.0226 | 3.04 | 808 | 1.3065 | 0.7 |
|
| 56 |
+
| 0.5437 | 4.04 | 1010 | 2.0397 | 0.7 |
|
| 57 |
+
| 0.0002 | 5.04 | 1212 | 1.8936 | 0.75 |
|
| 58 |
+
| 0.0003 | 6.04 | 1414 | 1.4473 | 0.8 |
|
| 59 |
+
| 0.0193 | 7.04 | 1616 | 1.1602 | 0.75 |
|
| 60 |
+
| 0.0001 | 8.04 | 1818 | 0.8922 | 0.9 |
|
| 61 |
+
| 0.0001 | 9.04 | 2020 | 1.0781 | 0.85 |
|
| 62 |
+
| 0.0 | 10.04 | 2222 | 1.1948 | 0.85 |
|
| 63 |
+
| 0.0 | 11.04 | 2424 | 1.2431 | 0.85 |
|
| 64 |
+
| 0.0 | 12.04 | 2626 | 1.2794 | 0.85 |
|
| 65 |
+
| 0.0 | 13.04 | 2828 | 1.3082 | 0.85 |
|
| 66 |
+
| 0.0 | 14.04 | 3030 | 1.3332 | 0.85 |
|
| 67 |
+
| 0.0 | 15.04 | 3232 | 1.3539 | 0.85 |
|
| 68 |
+
| 0.0 | 16.04 | 3434 | 1.3793 | 0.85 |
|
| 69 |
+
| 0.0 | 17.04 | 3636 | 1.4510 | 0.8 |
|
| 70 |
+
| 0.0 | 18.04 | 3838 | 1.5646 | 0.8 |
|
| 71 |
+
| 0.0 | 19.04 | 4040 | 1.6535 | 0.8 |
|
| 72 |
+
| 0.0 | 20.04 | 4242 | 1.7017 | 0.8 |
|
| 73 |
+
| 0.0 | 21.04 | 4444 | 1.7366 | 0.8 |
|
| 74 |
+
| 0.0 | 22.04 | 4646 | 1.7639 | 0.8 |
|
| 75 |
+
| 0.0 | 23.04 | 4848 | 1.7792 | 0.8 |
|
| 76 |
+
| 0.0 | 24.04 | 5050 | 1.7855 | 0.8 |
|
| 77 |
+
| 0.0 | 25.01 | 5100 | 1.7857 | 0.8 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.26.1
|
| 83 |
+
- Pytorch 1.12.1+cu116
|
| 84 |
+
- Datasets 2.4.0
|
| 85 |
+
- Tokenizers 0.12.1
|