billskar23
commited on
Commit
•
bee147f
1
Parent(s):
e67d852
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: cc-by-nc-4.0
|
4 |
+
base_model: MCG-NJU/videomae-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: videomae-base-finetuned-ucf101-subset
|
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 |
+
# videomae-base-finetuned-ucf101-subset
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5425
|
22 |
+
- Accuracy: 0.8645
|
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: 8
|
43 |
+
- eval_batch_size: 8
|
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: 148
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
54 |
+
| 2.1483 | 0.2568 | 38 | 1.8423 | 0.3857 |
|
55 |
+
| 0.8601 | 1.2568 | 76 | 0.9724 | 0.7 |
|
56 |
+
| 0.5181 | 2.2568 | 114 | 0.6129 | 0.7571 |
|
57 |
+
| 0.3207 | 3.2297 | 148 | 0.5354 | 0.8286 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.44.2
|
63 |
+
- Pytorch 1.12.0+cu113
|
64 |
+
- Datasets 3.0.0
|
65 |
+
- Tokenizers 0.19.1
|
runs/Sep25_08-06-46_50e493ebfcc4/events.out.tfevents.1727251610.50e493ebfcc4.6293.0
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:d0e78b3260becca810f3ad45bebf8f4d1119158430af2862ed202ea2ce197fe7
|
3 |
+
size 10136
|
runs/Sep25_08-06-46_50e493ebfcc4/events.out.tfevents.1727251867.50e493ebfcc4.6293.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70aee89fedeb4442635521e301bbfc2ab48783359f6cc092f423b560ad978847
|
3 |
+
size 411
|