End of training
Browse files- README.md +96 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model: MCG-NJU/videomae-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: videomae-base-finetuned-scratch_1
|
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 |
+
# videomae-base-finetuned-scratch_1
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.3906
|
21 |
+
- Accuracy: 0.8080
|
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: 12
|
42 |
+
- eval_batch_size: 12
|
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: 11856
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| 0.6811 | 0.03 | 330 | 0.6314 | 0.6547 |
|
54 |
+
| 0.6706 | 1.03 | 660 | 0.6354 | 0.6318 |
|
55 |
+
| 0.6581 | 2.03 | 990 | 0.6328 | 0.6375 |
|
56 |
+
| 0.5614 | 3.03 | 1320 | 0.5507 | 0.7135 |
|
57 |
+
| 0.438 | 4.03 | 1650 | 0.5440 | 0.7264 |
|
58 |
+
| 0.4569 | 5.03 | 1980 | 0.5532 | 0.7278 |
|
59 |
+
| 0.3614 | 6.03 | 2310 | 0.5283 | 0.7364 |
|
60 |
+
| 0.3514 | 7.03 | 2640 | 0.6700 | 0.7407 |
|
61 |
+
| 0.2796 | 8.03 | 2970 | 0.7974 | 0.7178 |
|
62 |
+
| 0.236 | 9.03 | 3300 | 0.6851 | 0.7722 |
|
63 |
+
| 0.2066 | 10.03 | 3630 | 0.7625 | 0.7708 |
|
64 |
+
| 0.2831 | 11.03 | 3960 | 0.7963 | 0.7708 |
|
65 |
+
| 0.1903 | 12.03 | 4290 | 1.0343 | 0.7722 |
|
66 |
+
| 0.1169 | 13.03 | 4620 | 0.8528 | 0.7865 |
|
67 |
+
| 0.3502 | 14.03 | 4950 | 0.9265 | 0.7966 |
|
68 |
+
| 0.1728 | 15.03 | 5280 | 0.8522 | 0.8209 |
|
69 |
+
| 0.0542 | 16.03 | 5610 | 1.0107 | 0.8052 |
|
70 |
+
| 0.0711 | 17.03 | 5940 | 0.9795 | 0.8080 |
|
71 |
+
| 0.0287 | 18.03 | 6270 | 1.1471 | 0.8095 |
|
72 |
+
| 0.1011 | 19.03 | 6600 | 1.0894 | 0.7851 |
|
73 |
+
| 0.0424 | 20.03 | 6930 | 1.1444 | 0.7822 |
|
74 |
+
| 0.0229 | 21.03 | 7260 | 1.3766 | 0.7822 |
|
75 |
+
| 0.058 | 22.03 | 7590 | 1.2796 | 0.7894 |
|
76 |
+
| 0.1045 | 23.03 | 7920 | 1.3585 | 0.7751 |
|
77 |
+
| 0.0379 | 24.03 | 8250 | 1.3156 | 0.7837 |
|
78 |
+
| 0.0945 | 25.03 | 8580 | 1.3047 | 0.7923 |
|
79 |
+
| 0.0528 | 26.03 | 8910 | 1.3670 | 0.7894 |
|
80 |
+
| 0.0002 | 27.03 | 9240 | 1.3398 | 0.7966 |
|
81 |
+
| 0.0562 | 28.03 | 9570 | 1.3444 | 0.7980 |
|
82 |
+
| 0.0002 | 29.03 | 9900 | 1.2679 | 0.8166 |
|
83 |
+
| 0.0018 | 30.03 | 10230 | 1.3748 | 0.7966 |
|
84 |
+
| 0.0371 | 31.03 | 10560 | 1.4094 | 0.8080 |
|
85 |
+
| 0.0157 | 32.03 | 10890 | 1.4391 | 0.8023 |
|
86 |
+
| 0.0001 | 33.03 | 11220 | 1.3831 | 0.8052 |
|
87 |
+
| 0.0001 | 34.03 | 11550 | 1.3971 | 0.8080 |
|
88 |
+
| 0.0041 | 35.03 | 11856 | 1.3906 | 0.8080 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.39.0
|
94 |
+
- Pytorch 2.2.1+cu121
|
95 |
+
- Datasets 2.18.0
|
96 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 344937368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9c13f1c49e0338cbe95989d81674407f7cced067e756e4162e0a95089fa204c
|
3 |
size 344937368
|