Hugging Face's logo

billskar23
/
videomae-base-videoMAE

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
billskar23 commited on
Commit
7af4899
•
1 Parent(s): b9b080b

Model save

Browse files
Files changed (4) hide show
  1. README.md +30 -30
  2. model.safetensors +1 -1
  3. runs/Sep26_16-02-25_hmudgx/events.out.tfevents.1727355747.hmudgx.918034.2 +2 -2
  4. runs/Sep26_16-54-02_hmudgx/events.out.tfevents.1727358844.hmudgx.917888.4 +2 -2
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 5.7047
25
- - Accuracy: 0.4615
26
- - Precision: 0.3357
27
- - Recall: 0.4615
28
- - F1: 0.3887
29
 
30
  ## Model description
31
 
@@ -45,38 +45,38 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 5e-05
48
- - train_batch_size: 8
49
- - eval_batch_size: 8
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_ratio: 0.1
54
- - training_steps: 5120
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.4543 | 1.0 | 256 | 0.6625 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
61
- | 0.3146 | 2.0 | 512 | 0.5416 | 0.6923 | 0.7949 | 0.6923 | 0.6205 |
62
- | 0.3278 | 3.0 | 768 | 2.1094 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
63
- | 0.2217 | 4.0 | 1024 | 1.9494 | 0.5385 | 0.4974 | 0.5385 | 0.5064 |
64
- | 0.0005 | 5.0 | 1280 | 3.3003 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
65
- | 0.0004 | 6.0 | 1536 | 4.0210 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
66
- | 0.1131 | 7.0 | 1792 | 2.7818 | 0.5385 | 0.4974 | 0.5385 | 0.5064 |
67
- | 0.0743 | 8.0 | 2048 | 4.6057 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
68
- | 0.0001 | 9.0 | 2304 | 4.7675 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
69
- | 0.0001 | 10.0 | 2560 | 5.2119 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
70
- | 0.0 | 11.0 | 2816 | 5.3397 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
71
- | 0.0 | 12.0 | 3072 | 5.4185 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
72
- | 0.0 | 13.0 | 3328 | 5.4844 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
73
- | 0.0 | 14.0 | 3584 | 5.5404 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
74
- | 0.0 | 15.0 | 3840 | 5.5875 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
75
- | 0.0 | 16.0 | 4096 | 5.6274 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
76
- | 0.0 | 17.0 | 4352 | 5.6595 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
77
- | 0.0 | 18.0 | 4608 | 5.6836 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
78
- | 0.0 | 19.0 | 4864 | 5.6993 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
79
- | 0.0 | 20.0 | 5120 | 5.7047 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
80
 
81
 
82
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 3.0328
25
+ - Accuracy: 0.6154
26
+ - Precision: 0.3787
27
+ - Recall: 0.6154
28
+ - F1: 0.4689
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 5e-05
48
+ - train_batch_size: 4
49
+ - eval_batch_size: 4
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_ratio: 0.1
54
+ - training_steps: 10240
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.3985 | 1.0 | 512 | 0.2857 | 0.9231 | 0.9316 | 0.9231 | 0.9211 |
61
+ | 0.4718 | 2.0 | 1024 | 1.4444 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
62
+ | 0.181 | 3.0 | 1536 | 3.1151 | 0.3846 | 0.3077 | 0.3846 | 0.3419 |
63
+ | 0.113 | 4.0 | 2048 | 1.9200 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
64
+ | 0.0771 | 5.0 | 2560 | 1.4445 | 0.5385 | 0.4974 | 0.5385 | 0.5064 |
65
+ | 0.0003 | 6.0 | 3072 | 1.6911 | 0.7692 | 0.7839 | 0.7692 | 0.7720 |
66
+ | 0.0002 | 7.0 | 3584 | 2.2123 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
67
+ | 0.0002 | 8.0 | 4096 | 3.1463 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
68
+ | 0.0001 | 9.0 | 4608 | 1.7846 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
69
+ | 0.0 | 10.0 | 5120 | 2.4646 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
70
+ | 0.0 | 11.0 | 5632 | 2.4743 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
71
+ | 0.0 | 12.0 | 6144 | 2.5687 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
72
+ | 0.0 | 13.0 | 6656 | 2.6551 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
73
+ | 0.0 | 14.0 | 7168 | 2.7365 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
74
+ | 0.0 | 15.0 | 7680 | 2.8134 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
75
+ | 0.0 | 16.0 | 8192 | 2.8798 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
76
+ | 0.0 | 17.0 | 8704 | 2.9415 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
77
+ | 0.0 | 18.0 | 9216 | 2.9896 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
78
+ | 0.0 | 19.0 | 9728 | 3.0225 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
79
+ | 0.0 | 20.0 | 10240 | 3.0328 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc3b9ee370dd21f651742d304c7a14020a1a00abc858aaeb45998da2e9ed003a
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87374ed47e771451bda21a448ffdb9f781469bde9f4c7a7efef0a953ef372326
3
  size 344937368
runs/Sep26_16-02-25_hmudgx/events.out.tfevents.1727355747.hmudgx.918034.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a1c64c4e4112037e0c2af8dab88df73015982fcfc1086ee90bab6aab745c1b5
3
- size 230582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3897c3a15821027805c9adb1d7e790fa49056a5c70ebee09cf941af995177764
3
+ size 230936
runs/Sep26_16-54-02_hmudgx/events.out.tfevents.1727358844.hmudgx.917888.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36b3c004b1000fbaf5b8b3323d18fc83f1978d8d9c329625da0054c7c2e315b5
3
- size 6988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71ddc70c2e3efb3776661a816a9c70eff68cb97ed26f892095162846ffa9755
3
+ size 7609