Hugging Face's logo

PaaP
/
videomae-base-finetuned-masa

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Model card Files
xet
Metrics Community
PaaP commited on
Commit
f1bf219
·
verified ·
1 Parent(s): e062a5a

End of training

Browse files
Files changed (4) hide show
  1. README.md +20 -25
  2. emissions.csv +1 -0
  3. model.safetensors +1 -1
  4. runs/Sep04_10-02-48_3d3d7d19998a/events.out.tfevents.1725444173.3d3d7d19998a.8960.0 +2 -2
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 4.3612
22
- - Accuracy: 0.4
23
 
24
  ## Model description
25
 
@@ -45,32 +45,27 @@ The following hyperparameters were used during training:
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: 240
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 1.6826 | 0.05 | 12 | 1.7279 | 0.0 |
55
- | 1.2427 | 1.05 | 24 | 1.6551 | 0.4 |
56
- | 0.89 | 2.05 | 36 | 1.5625 | 0.4 |
57
- | 1.1683 | 3.05 | 48 | 2.1126 | 0.4 |
58
- | 0.8243 | 4.05 | 60 | 2.8933 | 0.2 |
59
- | 0.291 | 5.05 | 72 | 2.3560 | 0.2 |
60
- | 0.3028 | 6.05 | 84 | 3.6436 | 0.2 |
61
- | 0.0613 | 7.05 | 96 | 3.0208 | 0.4 |
62
- | 0.0053 | 8.05 | 108 | 3.6414 | 0.4 |
63
- | 0.003 | 9.05 | 120 | 3.9191 | 0.4 |
64
- | 0.0026 | 10.05 | 132 | 3.9548 | 0.4 |
65
- | 0.0016 | 11.05 | 144 | 4.1584 | 0.4 |
66
- | 0.0015 | 12.05 | 156 | 4.2011 | 0.4 |
67
- | 0.0015 | 13.05 | 168 | 4.2129 | 0.4 |
68
- | 0.0013 | 14.05 | 180 | 4.2635 | 0.4 |
69
- | 0.0014 | 15.05 | 192 | 4.3133 | 0.4 |
70
- | 0.0013 | 16.05 | 204 | 4.3490 | 0.4 |
71
- | 0.0011 | 17.05 | 216 | 4.3620 | 0.4 |
72
- | 0.0011 | 18.05 | 228 | 4.3611 | 0.4 |
73
- | 0.0013 | 19.05 | 240 | 4.3612 | 0.4 |
74
 
75
 
76
  ### Framework versions
 
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: 0.0031
22
+ - Accuracy: 1.0
23
 
24
  ## Model description
25
 
 
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: 225
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
54
+ | 1.601 | 0.0667 | 15 | 1.3659 | 0.8 |
55
+ | 1.5638 | 1.0667 | 30 | 1.4763 | 0.4 |
56
+ | 1.1535 | 2.0667 | 45 | 1.2764 | 0.6 |
57
+ | 0.637 | 3.0667 | 60 | 0.6158 | 0.8 |
58
+ | 0.809 | 4.0667 | 75 | 1.1473 | 0.4 |
59
+ | 0.6648 | 5.0667 | 90 | 0.6767 | 0.6 |
60
+ | 0.4322 | 6.0667 | 105 | 0.8144 | 0.8 |
61
+ | 0.3076 | 7.0667 | 120 | 0.1087 | 1.0 |
62
+ | 0.0364 | 8.0667 | 135 | 0.1052 | 1.0 |
63
+ | 0.0037 | 9.0667 | 150 | 0.0106 | 1.0 |
64
+ | 0.0027 | 10.0667 | 165 | 0.0075 | 1.0 |
65
+ | 0.0029 | 11.0667 | 180 | 0.0058 | 1.0 |
66
+ | 0.0049 | 12.0667 | 195 | 0.0033 | 1.0 |
67
+ | 0.0028 | 13.0667 | 210 | 0.0031 | 1.0 |
68
+ | 0.0027 | 14.0667 | 225 | 0.0031 | 1.0 |
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
emissions.csv CHANGED
@@ -3,3 +3,4 @@ timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_
3
  2024-09-04T09:30:05,07135390-120f-4b22-bc02-3e9fbfc96307,codecarbon,348.34844613075256,0.006889514740437022,0.00826280388335038,India,IND,,N,,
4
  2024-09-04T09:34:45,e6c76d5b-d2af-4078-b935-f1b454de43c7,codecarbon,86.87316513061523,0.0016960591731561953,0.0020341351822781763,India,IND,,N,,
5
  2024-09-04T09:58:59,9f44ad40-6b0c-48a7-8486-bc5a13e055d4,codecarbon,771.8074398040771,0.016318435453230116,0.01957119433125696,India,IND,,N,,
 
 
3
  2024-09-04T09:30:05,07135390-120f-4b22-bc02-3e9fbfc96307,codecarbon,348.34844613075256,0.006889514740437022,0.00826280388335038,India,IND,,N,,
4
  2024-09-04T09:34:45,e6c76d5b-d2af-4078-b935-f1b454de43c7,codecarbon,86.87316513061523,0.0016960591731561953,0.0020341351822781763,India,IND,,N,,
5
  2024-09-04T09:58:59,9f44ad40-6b0c-48a7-8486-bc5a13e055d4,codecarbon,771.8074398040771,0.016318435453230116,0.01957119433125696,India,IND,,N,,
6
+ 2024-09-04T10:14:42,264f7f3a-1743-42f1-8789-f4cf88d13a08,codecarbon,708.4137392044067,0.013841380190026958,0.016600386862345117,India,IND,,N,,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9c0fe72d4cfee469218f1664d51382b2708a5a1c1425e9c9b6df094a08886a4
3
  size 344946604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae0772e0aaac7fdea869d1883d1d6a04339e6793906c49be8937f7940fd3236
3
  size 344946604
runs/Sep04_10-02-48_3d3d7d19998a/events.out.tfevents.1725444173.3d3d7d19998a.8960.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f1f58f7583187aaca0344956c83cb8c681362c20f33fd525631aa47264b309b
3
- size 14176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7852502908e42d0054bb6ea91e9ab8fba9d77a0d45e693753456162d287d69
3
+ size 15064