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
4dbfe70
·
verified ·
1 Parent(s): 05a65c0

Model save

Browse files
Files changed (3) hide show
  1. README.md +26 -26
  2. model.safetensors +1 -1
  3. runs/Sep26_21-55-29_hmudgx/events.out.tfevents.1727376931.hmudgx.1191083.6 +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: 5.5357
25
- - Accuracy: 0.4667
26
- - Precision: 0.2667
27
- - Recall: 0.4667
28
- - F1: 0.3394
29
 
30
  ## Model description
31
 
@@ -51,32 +51,32 @@ The following hyperparameters were used during training:
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: 10220
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.574 | 1.0 | 512 | 0.6358 | 0.5333 | 0.5205 | 0.5333 | 0.4593 |
61
- | 0.4654 | 2.0 | 1024 | 0.2525 | 0.8667 | 0.8933 | 0.8667 | 0.8630 |
62
- | 0.3926 | 3.0 | 1536 | 2.2142 | 0.6 | 0.7714 | 0.6 | 0.5045 |
63
- | 0.321 | 4.0 | 2048 | 3.5357 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
64
- | 0.0003 | 5.0 | 2560 | 3.2061 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
65
- | 0.0033 | 6.0 | 3072 | 3.7966 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
66
- | 0.0004 | 7.0 | 3584 | 4.5518 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
67
- | 0.0008 | 8.0 | 4096 | 4.4146 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
68
- | 0.0001 | 9.0 | 4608 | 4.5341 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
69
- | 0.0 | 10.0 | 5120 | 5.9337 | 0.4 | 0.2462 | 0.4 | 0.3048 |
70
- | 0.0001 | 11.0 | 5632 | 4.0873 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
71
- | 0.0001 | 12.0 | 6144 | 4.9372 | 0.4667 | 0.2667 | 0.4667 | 0.3394 |
72
- | 0.1371 | 13.0 | 6656 | 4.5830 | 0.4667 | 0.4222 | 0.4667 | 0.4133 |
73
- | 0.0 | 14.0 | 7168 | 5.2331 | 0.4 | 0.2462 | 0.4 | 0.3048 |
74
- | 0.0 | 15.0 | 7680 | 5.3213 | 0.4 | 0.2462 | 0.4 | 0.3048 |
75
- | 0.0 | 16.0 | 8192 | 5.3904 | 0.4 | 0.2462 | 0.4 | 0.3048 |
76
- | 0.0 | 17.0 | 8704 | 5.4466 | 0.4 | 0.2462 | 0.4 | 0.3048 |
77
- | 0.0 | 18.0 | 9216 | 5.4930 | 0.4 | 0.2462 | 0.4 | 0.3048 |
78
- | 0.0 | 19.0 | 9728 | 5.5243 | 0.4 | 0.2462 | 0.4 | 0.3048 |
79
- | 0.0 | 19.9609 | 10220 | 5.5357 | 0.4667 | 0.2667 | 0.4667 | 0.3394 |
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: 1.3778
25
+ - Accuracy: 0.8182
26
+ - Precision: 0.8701
27
+ - Recall: 0.8182
28
+ - F1: 0.8152
29
 
30
  ## Model description
31
 
 
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
+ | 0.6826 | 1.0 | 513 | 0.3076 | 1.0 | 1.0 | 1.0 | 1.0 |
61
+ | 0.3488 | 2.0 | 1026 | 0.6793 | 0.7273 | 0.8295 | 0.7273 | 0.7133 |
62
+ | 0.4113 | 3.0 | 1539 | 0.5896 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
63
+ | 0.0011 | 4.0 | 2052 | 0.9988 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
64
+ | 0.0708 | 5.0 | 2565 | 3.4474 | 0.5455 | 0.7727 | 0.5455 | 0.4589 |
65
+ | 0.2064 | 6.0 | 3078 | 0.7651 | 0.6364 | 0.7980 | 0.6364 | 0.5974 |
66
+ | 0.0001 | 7.0 | 3591 | 1.3749 | 0.6364 | 0.7980 | 0.6364 | 0.5974 |
67
+ | 0.1675 | 8.0 | 4104 | 0.7749 | 0.7273 | 0.8295 | 0.7273 | 0.7133 |
68
+ | 0.0005 | 9.0 | 4617 | 0.6269 | 0.9091 | 0.9242 | 0.9091 | 0.9091 |
69
+ | 0.0001 | 10.0 | 5130 | 1.5145 | 0.6364 | 0.7980 | 0.6364 | 0.5974 |
70
+ | 0.0 | 11.0 | 5643 | 1.0528 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
71
+ | 0.0 | 12.0 | 6156 | 1.1364 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
72
+ | 0.0 | 13.0 | 6669 | 1.1880 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
73
+ | 0.0 | 14.0 | 7182 | 1.2319 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
74
+ | 0.0 | 15.0 | 7695 | 1.2673 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
75
+ | 0.0 | 16.0 | 8208 | 1.3042 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
76
+ | 0.0 | 17.0 | 8721 | 1.3329 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
77
+ | 0.0 | 18.0 | 9234 | 1.3562 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
78
+ | 0.0 | 19.0 | 9747 | 1.3716 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
79
+ | 0.0 | 19.9610 | 10240 | 1.3778 | 0.8182 | 0.8701 | 0.8182 | 0.8152 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dd3a6069c4bc0d39015d29820e15ccbdb77f2a18ad6425469c48d7d3066a4bd
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe9ddcc7a8d44c575d0aec8804067e6144890dd3b780c8faa4cabc29bf0cc4f9
3
  size 344937368
runs/Sep26_21-55-29_hmudgx/events.out.tfevents.1727376931.hmudgx.1191083.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbfa9adf9a6d4b48b0cdbe533f4b120232b0ef21135f363bf1c9a0873165e12e
3
- size 230582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43cea1b10431195eb6e93a8fed0cb0d29f24fe3d662a890c8f1ba1225d49dc4
3
+ size 230936