Steve Chiou
commited on
Commit
•
22c33bf
1
Parent(s):
9f887eb
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: videomae-large-finetuned-kinetics-finetuned-engine-subset-R2-K400-20230418_3
|
| 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-large-finetuned-kinetics-finetuned-engine-subset-R2-K400-20230418_3
|
| 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: 3.1972
|
| 20 |
+
- Accuracy: 0.2647
|
| 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: 6
|
| 41 |
+
- eval_batch_size: 6
|
| 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: 2700
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 2.5562 | 0.02 | 55 | 2.5746 | 0.0221 |
|
| 53 |
+
| 2.4543 | 1.02 | 110 | 2.5524 | 0.0956 |
|
| 54 |
+
| 2.1443 | 2.02 | 165 | 2.5214 | 0.1103 |
|
| 55 |
+
| 1.6604 | 3.02 | 220 | 2.6415 | 0.1397 |
|
| 56 |
+
| 1.5847 | 4.02 | 275 | 2.9843 | 0.0735 |
|
| 57 |
+
| 1.4657 | 5.02 | 330 | 2.7476 | 0.1471 |
|
| 58 |
+
| 1.0823 | 6.02 | 385 | 3.0872 | 0.1471 |
|
| 59 |
+
| 1.0672 | 7.02 | 440 | 2.9539 | 0.2206 |
|
| 60 |
+
| 0.7241 | 8.02 | 495 | 3.5364 | 0.1103 |
|
| 61 |
+
| 0.6532 | 9.02 | 550 | 3.1972 | 0.2647 |
|
| 62 |
+
| 0.6476 | 10.02 | 605 | 4.1289 | 0.0735 |
|
| 63 |
+
| 0.3725 | 11.02 | 660 | 4.4710 | 0.0588 |
|
| 64 |
+
| 0.7363 | 12.02 | 715 | 4.9241 | 0.0662 |
|
| 65 |
+
| 0.3136 | 13.02 | 770 | 4.8217 | 0.1176 |
|
| 66 |
+
| 0.3154 | 14.02 | 825 | 4.2717 | 0.1838 |
|
| 67 |
+
| 0.309 | 15.02 | 880 | 4.9466 | 0.0588 |
|
| 68 |
+
| 0.3094 | 16.02 | 935 | 5.5394 | 0.0147 |
|
| 69 |
+
| 0.3333 | 17.02 | 990 | 5.0940 | 0.0956 |
|
| 70 |
+
| 0.2299 | 18.02 | 1045 | 6.3148 | 0.0074 |
|
| 71 |
+
| 0.2257 | 19.02 | 1100 | 5.3869 | 0.0588 |
|
| 72 |
+
| 0.255 | 20.02 | 1155 | 6.4134 | 0.0147 |
|
| 73 |
+
| 0.2335 | 21.02 | 1210 | 6.1413 | 0.0441 |
|
| 74 |
+
| 0.3507 | 22.02 | 1265 | 6.2911 | 0.0074 |
|
| 75 |
+
| 0.1463 | 23.02 | 1320 | 6.5273 | 0.0074 |
|
| 76 |
+
| 0.193 | 24.02 | 1375 | 6.6533 | 0.0074 |
|
| 77 |
+
| 0.1167 | 25.02 | 1430 | 6.8094 | 0.0 |
|
| 78 |
+
| 0.1168 | 26.02 | 1485 | 6.7632 | 0.0 |
|
| 79 |
+
| 0.0511 | 27.02 | 1540 | 7.0046 | 0.0074 |
|
| 80 |
+
| 0.1336 | 28.02 | 1595 | 7.2877 | 0.0 |
|
| 81 |
+
| 0.1518 | 29.02 | 1650 | 7.3102 | 0.0 |
|
| 82 |
+
| 0.1972 | 30.02 | 1705 | 7.1632 | 0.0 |
|
| 83 |
+
| 0.0605 | 31.02 | 1760 | 7.2970 | 0.0 |
|
| 84 |
+
| 0.1633 | 32.02 | 1815 | 7.3427 | 0.0 |
|
| 85 |
+
| 0.1902 | 33.02 | 1870 | 7.4095 | 0.0 |
|
| 86 |
+
| 0.132 | 34.02 | 1925 | 7.3169 | 0.0 |
|
| 87 |
+
| 0.1226 | 35.02 | 1980 | 7.4196 | 0.0074 |
|
| 88 |
+
| 0.115 | 36.02 | 2035 | 7.3248 | 0.0074 |
|
| 89 |
+
| 0.1348 | 37.02 | 2090 | 7.1318 | 0.0 |
|
| 90 |
+
| 0.1684 | 38.02 | 2145 | 7.6482 | 0.0 |
|
| 91 |
+
| 0.0722 | 39.02 | 2200 | 7.5944 | 0.0074 |
|
| 92 |
+
| 0.1155 | 40.02 | 2255 | 7.5615 | 0.0 |
|
| 93 |
+
| 0.1425 | 41.02 | 2310 | 7.6454 | 0.0074 |
|
| 94 |
+
| 0.1552 | 42.02 | 2365 | 7.4774 | 0.0074 |
|
| 95 |
+
| 0.1078 | 43.02 | 2420 | 7.3991 | 0.0074 |
|
| 96 |
+
| 0.1169 | 44.02 | 2475 | 7.3240 | 0.0 |
|
| 97 |
+
| 0.1438 | 45.02 | 2530 | 7.4133 | 0.0 |
|
| 98 |
+
| 0.1227 | 46.02 | 2585 | 7.4592 | 0.0 |
|
| 99 |
+
| 0.0716 | 47.02 | 2640 | 7.5590 | 0.0 |
|
| 100 |
+
| 0.2077 | 48.02 | 2695 | 7.5708 | 0.0 |
|
| 101 |
+
| 0.0731 | 49.0 | 2700 | 7.5710 | 0.0 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- Transformers 4.26.1
|
| 107 |
+
- Pytorch 1.12.1+cu113
|
| 108 |
+
- Datasets 2.10.1
|
| 109 |
+
- Tokenizers 0.13.2
|