Commit
•
a235b68
1
Parent(s):
3f30d53
Model save
Browse files- README.md +110 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: MCG-NJU/videomae-large-finetuned-kinetics
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: MAE-CT-CPC-Dicotomized-n0-m1-d1-v9
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# MAE-CT-CPC-Dicotomized-n0-m1-d1-v9
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-large-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-large-finetuned-kinetics) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.6419
|
| 22 |
+
- Accuracy: 0.5
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- training_steps: 2400
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 0.6819 | 0.0204 | 49 | 0.6641 | 0.5789 |
|
| 55 |
+
| 0.6201 | 1.0204 | 98 | 0.6368 | 0.5789 |
|
| 56 |
+
| 0.6787 | 2.0204 | 147 | 0.6109 | 0.5789 |
|
| 57 |
+
| 0.6484 | 3.0204 | 196 | 0.6305 | 0.6316 |
|
| 58 |
+
| 0.6357 | 4.0204 | 245 | 0.6794 | 0.5263 |
|
| 59 |
+
| 0.5692 | 5.0204 | 294 | 0.6938 | 0.5263 |
|
| 60 |
+
| 0.658 | 6.0204 | 343 | 0.6696 | 0.5789 |
|
| 61 |
+
| 0.5112 | 7.0204 | 392 | 0.5669 | 0.6316 |
|
| 62 |
+
| 0.3719 | 8.0204 | 441 | 0.8023 | 0.6316 |
|
| 63 |
+
| 0.4573 | 9.0204 | 490 | 0.5991 | 0.6316 |
|
| 64 |
+
| 0.2915 | 10.0204 | 539 | 0.7899 | 0.6842 |
|
| 65 |
+
| 0.3723 | 11.0204 | 588 | 0.9848 | 0.5263 |
|
| 66 |
+
| 0.1372 | 12.0204 | 637 | 0.9510 | 0.6316 |
|
| 67 |
+
| 0.0066 | 13.0204 | 686 | 1.1872 | 0.5789 |
|
| 68 |
+
| 0.2218 | 14.0204 | 735 | 1.1692 | 0.7368 |
|
| 69 |
+
| 0.7666 | 15.0204 | 784 | 1.1125 | 0.6842 |
|
| 70 |
+
| 0.2171 | 16.0204 | 833 | 1.2615 | 0.7368 |
|
| 71 |
+
| 0.1152 | 17.0204 | 882 | 1.3683 | 0.7368 |
|
| 72 |
+
| 0.1941 | 18.0204 | 931 | 1.3915 | 0.7368 |
|
| 73 |
+
| 0.0233 | 19.0204 | 980 | 1.5972 | 0.5789 |
|
| 74 |
+
| 0.2367 | 20.0204 | 1029 | 1.7445 | 0.6842 |
|
| 75 |
+
| 0.1575 | 21.0204 | 1078 | 2.4036 | 0.6316 |
|
| 76 |
+
| 0.0008 | 22.0204 | 1127 | 2.2633 | 0.6316 |
|
| 77 |
+
| 0.019 | 23.0204 | 1176 | 2.2078 | 0.6842 |
|
| 78 |
+
| 0.0006 | 24.0204 | 1225 | 2.1281 | 0.6316 |
|
| 79 |
+
| 0.0004 | 25.0204 | 1274 | 2.0100 | 0.7368 |
|
| 80 |
+
| 0.0002 | 26.0204 | 1323 | 2.3862 | 0.6316 |
|
| 81 |
+
| 0.0003 | 27.0204 | 1372 | 2.1579 | 0.6842 |
|
| 82 |
+
| 0.0372 | 28.0204 | 1421 | 2.1226 | 0.6842 |
|
| 83 |
+
| 0.1547 | 29.0204 | 1470 | 2.4949 | 0.6842 |
|
| 84 |
+
| 0.0015 | 30.0204 | 1519 | 1.8815 | 0.6842 |
|
| 85 |
+
| 0.0005 | 31.0204 | 1568 | 2.2582 | 0.6316 |
|
| 86 |
+
| 0.0002 | 32.0204 | 1617 | 2.1774 | 0.6316 |
|
| 87 |
+
| 0.0001 | 33.0204 | 1666 | 2.2222 | 0.6316 |
|
| 88 |
+
| 0.0001 | 34.0204 | 1715 | 2.3560 | 0.6316 |
|
| 89 |
+
| 0.0001 | 35.0204 | 1764 | 2.3904 | 0.6316 |
|
| 90 |
+
| 0.0001 | 36.0204 | 1813 | 2.2240 | 0.7368 |
|
| 91 |
+
| 0.0002 | 37.0204 | 1862 | 2.2880 | 0.6842 |
|
| 92 |
+
| 0.0002 | 38.0204 | 1911 | 2.3010 | 0.6842 |
|
| 93 |
+
| 0.0001 | 39.0204 | 1960 | 2.3124 | 0.6842 |
|
| 94 |
+
| 0.0001 | 40.0204 | 2009 | 2.2903 | 0.6842 |
|
| 95 |
+
| 0.1744 | 41.0204 | 2058 | 2.3067 | 0.6842 |
|
| 96 |
+
| 0.0001 | 42.0204 | 2107 | 2.3422 | 0.6842 |
|
| 97 |
+
| 0.0001 | 43.0204 | 2156 | 2.3477 | 0.6842 |
|
| 98 |
+
| 0.0001 | 44.0204 | 2205 | 2.3783 | 0.6316 |
|
| 99 |
+
| 0.0001 | 45.0204 | 2254 | 2.3447 | 0.6842 |
|
| 100 |
+
| 0.0001 | 46.0204 | 2303 | 2.3415 | 0.6842 |
|
| 101 |
+
| 0.0001 | 47.0204 | 2352 | 2.3419 | 0.6842 |
|
| 102 |
+
| 0.0001 | 48.02 | 2400 | 2.3470 | 0.6842 |
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
### Framework versions
|
| 106 |
+
|
| 107 |
+
- Transformers 4.45.2
|
| 108 |
+
- Pytorch 2.0.1+cu117
|
| 109 |
+
- Datasets 3.0.1
|
| 110 |
+
- Tokenizers 0.20.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1215496208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f14ec964d6fa8f9805d37ab7ca43f0c447a7d1319cc7955d6120c28f3580ef9b
|
| 3 |
size 1215496208
|