Commit
•
cc3c8b2
1
Parent(s):
0fe6a09
End of training
Browse files- README.md +73 -0
- config.json +39 -0
- model.safetensors +3 -0
- preprocessor_config.json +42 -0
- runs/Jun05_17-01-28_USER-20231127DF/events.out.tfevents.1717578101.USER-20231127DF.4964.2 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-custom-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/v8zohmjq)
|
17 |
+
[<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/v8zohmjq)
|
18 |
+
[<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/v8zohmjq)
|
19 |
+
# videomae-base-finetuned-kinetics-finetuned-custom-subset
|
20 |
+
|
21 |
+
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.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.9783
|
24 |
+
- Accuracy: 0.7564
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 4
|
45 |
+
- eval_batch_size: 4
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- training_steps: 710
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
56 |
+
| 0.6747 | 0.1014 | 72 | 0.6989 | 0.7308 |
|
57 |
+
| 0.5585 | 1.1014 | 144 | 0.7504 | 0.7308 |
|
58 |
+
| 1.0181 | 2.1014 | 216 | 0.5370 | 0.6795 |
|
59 |
+
| 0.5883 | 3.1014 | 288 | 0.6710 | 0.7308 |
|
60 |
+
| 0.3918 | 4.1014 | 360 | 0.5803 | 0.7692 |
|
61 |
+
| 0.3903 | 5.1014 | 432 | 0.5857 | 0.7436 |
|
62 |
+
| 0.2452 | 6.1014 | 504 | 0.8492 | 0.7308 |
|
63 |
+
| 0.4107 | 7.1014 | 576 | 0.8475 | 0.7308 |
|
64 |
+
| 0.099 | 8.1014 | 648 | 0.9360 | 0.7436 |
|
65 |
+
| 0.0679 | 9.0873 | 710 | 0.9783 | 0.7564 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.42.0.dev0
|
71 |
+
- Pytorch 2.1.1
|
72 |
+
- Datasets 2.13.2
|
73 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MCG-NJU/videomae-base-finetuned-kinetics",
|
3 |
+
"architectures": [
|
4 |
+
"VideoMAEForVideoClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"decoder_hidden_size": 384,
|
8 |
+
"decoder_intermediate_size": 1536,
|
9 |
+
"decoder_num_attention_heads": 6,
|
10 |
+
"decoder_num_hidden_layers": 4,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "0",
|
16 |
+
"1": "1"
|
17 |
+
},
|
18 |
+
"image_size": 224,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"0": 0,
|
23 |
+
"1": 1
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"model_type": "videomae",
|
27 |
+
"norm_pix_loss": false,
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_channels": 3,
|
30 |
+
"num_frames": 16,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"patch_size": 16,
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"qkv_bias": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.42.0.dev0",
|
37 |
+
"tubelet_size": 2,
|
38 |
+
"use_mean_pooling": true
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aea1d7cddc4a72717b51c444aad8ec69625357095f216c3dfaa8f0b34cb59af4
|
3 |
+
size 344937328
|
preprocessor_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"videos",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"return_tensors",
|
15 |
+
"data_format",
|
16 |
+
"input_data_format"
|
17 |
+
],
|
18 |
+
"crop_size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
},
|
22 |
+
"do_center_crop": true,
|
23 |
+
"do_normalize": true,
|
24 |
+
"do_rescale": true,
|
25 |
+
"do_resize": true,
|
26 |
+
"image_mean": [
|
27 |
+
0.485,
|
28 |
+
0.456,
|
29 |
+
0.406
|
30 |
+
],
|
31 |
+
"image_processor_type": "VideoMAEImageProcessor",
|
32 |
+
"image_std": [
|
33 |
+
0.229,
|
34 |
+
0.224,
|
35 |
+
0.225
|
36 |
+
],
|
37 |
+
"resample": 2,
|
38 |
+
"rescale_factor": 0.00392156862745098,
|
39 |
+
"size": {
|
40 |
+
"shortest_edge": 224
|
41 |
+
}
|
42 |
+
}
|
runs/Jun05_17-01-28_USER-20231127DF/events.out.tfevents.1717578101.USER-20231127DF.4964.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f2bfef21bdb953230e18f267a112b2648eb08216b441b355868ab1a783deb32
|
3 |
+
size 23731
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bda6c298ca3608b700c5cf7d79bf6a241dbecaa20b28a3169bd8d3aaba6f1100
|
3 |
+
size 5240
|