Commit
•
329c952
1
Parent(s):
d024d2a
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model: MCG-NJU/videomae-base-finetuned-kinetics
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: videomae-base-finetuned-kinetics-finetuned-freeway-subset
|
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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/huangyangyu/huggingface/runs/3e8psy1e)
|
17 |
+
# videomae-base-finetuned-kinetics-finetuned-freeway-subset
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0016
|
22 |
+
- Accuracy: 1.0
|
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: 5e-05
|
42 |
+
- train_batch_size: 5
|
43 |
+
- eval_batch_size: 5
|
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: 1800
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| 0.6551 | 0.02 | 36 | 0.7171 | 0.5 |
|
55 |
+
| 0.6085 | 1.02 | 72 | 0.7057 | 0.5 |
|
56 |
+
| 0.5876 | 2.02 | 108 | 0.5834 | 0.75 |
|
57 |
+
| 0.5757 | 3.02 | 144 | 0.5360 | 0.7143 |
|
58 |
+
| 0.7017 | 4.02 | 180 | 0.4589 | 0.7143 |
|
59 |
+
| 0.5681 | 5.02 | 216 | 0.3667 | 0.8214 |
|
60 |
+
| 0.3418 | 6.02 | 252 | 0.2312 | 0.9286 |
|
61 |
+
| 0.6408 | 7.02 | 288 | 0.2724 | 0.8929 |
|
62 |
+
| 0.3846 | 8.02 | 324 | 0.1288 | 0.9643 |
|
63 |
+
| 0.1551 | 9.02 | 360 | 0.6198 | 0.8214 |
|
64 |
+
| 0.4879 | 10.02 | 396 | 0.3241 | 0.8571 |
|
65 |
+
| 0.0982 | 11.02 | 432 | 0.1815 | 0.9286 |
|
66 |
+
| 0.112 | 12.02 | 468 | 0.2504 | 0.9643 |
|
67 |
+
| 0.3627 | 13.02 | 504 | 0.2357 | 0.9643 |
|
68 |
+
| 0.2329 | 14.02 | 540 | 0.6101 | 0.8571 |
|
69 |
+
| 0.141 | 15.02 | 576 | 0.0218 | 1.0 |
|
70 |
+
| 0.1755 | 16.02 | 612 | 0.0791 | 0.9643 |
|
71 |
+
| 0.079 | 17.02 | 648 | 0.1167 | 0.9643 |
|
72 |
+
| 0.0859 | 18.02 | 684 | 0.0118 | 1.0 |
|
73 |
+
| 0.0131 | 19.02 | 720 | 0.0020 | 1.0 |
|
74 |
+
| 0.0014 | 20.02 | 756 | 0.0054 | 1.0 |
|
75 |
+
| 0.0008 | 21.02 | 792 | 0.0841 | 0.9286 |
|
76 |
+
| 0.0024 | 22.02 | 828 | 0.0852 | 0.9643 |
|
77 |
+
| 0.1803 | 23.02 | 864 | 0.0005 | 1.0 |
|
78 |
+
| 0.0001 | 24.02 | 900 | 0.0379 | 0.9643 |
|
79 |
+
| 0.0012 | 25.02 | 936 | 0.0705 | 0.9643 |
|
80 |
+
| 0.0018 | 26.02 | 972 | 0.0010 | 1.0 |
|
81 |
+
| 0.0007 | 27.02 | 1008 | 0.0210 | 1.0 |
|
82 |
+
| 0.0028 | 28.02 | 1044 | 0.0030 | 1.0 |
|
83 |
+
| 0.0465 | 29.02 | 1080 | 0.0005 | 1.0 |
|
84 |
+
| 0.0004 | 30.02 | 1116 | 0.0011 | 1.0 |
|
85 |
+
| 0.0016 | 31.02 | 1152 | 0.0005 | 1.0 |
|
86 |
+
| 0.0 | 32.02 | 1188 | 0.0012 | 1.0 |
|
87 |
+
| 0.0002 | 33.02 | 1224 | 0.0001 | 1.0 |
|
88 |
+
| 0.0315 | 34.02 | 1260 | 0.0027 | 1.0 |
|
89 |
+
| 0.0253 | 35.02 | 1296 | 0.0003 | 1.0 |
|
90 |
+
| 0.0011 | 36.02 | 1332 | 0.0022 | 1.0 |
|
91 |
+
| 0.0001 | 37.02 | 1368 | 0.0006 | 1.0 |
|
92 |
+
| 0.0007 | 38.02 | 1404 | 0.0120 | 1.0 |
|
93 |
+
| 0.0001 | 39.02 | 1440 | 0.1001 | 0.9643 |
|
94 |
+
| 0.0005 | 40.02 | 1476 | 0.0331 | 0.9643 |
|
95 |
+
| 0.0009 | 41.02 | 1512 | 0.0418 | 0.9643 |
|
96 |
+
| 0.0035 | 42.02 | 1548 | 0.0761 | 0.9643 |
|
97 |
+
| 0.0001 | 43.02 | 1584 | 0.0020 | 1.0 |
|
98 |
+
| 0.0001 | 44.02 | 1620 | 0.0020 | 1.0 |
|
99 |
+
| 0.0 | 45.02 | 1656 | 0.0010 | 1.0 |
|
100 |
+
| 0.0001 | 46.02 | 1692 | 0.0009 | 1.0 |
|
101 |
+
| 0.0005 | 47.02 | 1728 | 0.0012 | 1.0 |
|
102 |
+
| 0.0001 | 48.02 | 1764 | 0.0015 | 1.0 |
|
103 |
+
| 0.0002 | 49.02 | 1800 | 0.0016 | 1.0 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.42.0.dev0
|
109 |
+
- Pytorch 2.1.1
|
110 |
+
- Datasets 2.19.2
|
111 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 344937328
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff9d7f05c364d93a37b0bed932a11eccb89417d3e543365fbc567f7e640607f6
|
3 |
size 344937328
|
runs/Jun09_11-56-40_USER-20231127DF/events.out.tfevents.1717905408.USER-20231127DF.21184.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6865bd7722deb5427f3c523a2062a2a0d1e42c9ac511916c25578859908f8e0e
|
3 |
+
size 59637
|