Model save
Browse files
README.md
CHANGED
@@ -1,3 +1,70 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-nc-4.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: videomae-base-finetuned-numbers-augmented
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# videomae-base-finetuned-numbers-augmented
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1494
|
24 |
+
- Accuracy: 0.9559
|
25 |
+
- F1: 0.9562
|
26 |
+
- Precision: 0.9568
|
27 |
+
- Recall: 0.9565
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 4
|
48 |
+
- eval_batch_size: 4
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- training_steps: 2816
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
59 |
+
| 0.8968 | 0.25 | 704 | 0.8689 | 0.6878 | 0.6885 | 0.7423 | 0.6886 |
|
60 |
+
| 0.5002 | 1.25 | 1408 | 0.4374 | 0.8542 | 0.8531 | 0.8718 | 0.8535 |
|
61 |
+
| 0.3627 | 2.25 | 2112 | 0.1109 | 0.9623 | 0.9618 | 0.9647 | 0.9614 |
|
62 |
+
| 0.0289 | 3.25 | 2816 | 0.0374 | 0.9880 | 0.9880 | 0.9881 | 0.9880 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.40.0
|
68 |
+
- Pytorch 2.1.0+cu121
|
69 |
+
- Datasets 2.18.0
|
70 |
+
- Tokenizers 0.19.1
|
runs/Apr30_22-59-34_blackhorse/events.out.tfevents.1714517431.blackhorse.5540.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3865583ea7b2b5898544d6533c51dd6308120b9b7034a64ebc3abaa0e9c42673
|
3 |
+
size 560
|