deschamps-g commited on
Commit
36bf0b9
1 Parent(s): 25cab10

Model save

Browse files
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.7570
22
- - Accuracy: 0.9023
23
- - F1: 0.9016
24
 
25
  ## Model description
26
 
@@ -46,28 +46,42 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - training_steps: 741
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss |
54
- |:-------------:|:-------:|:-----:|:--------:|:------:|:---------------:|
55
- | 1.3533 | 0.05 | 741 | 0.8393 | 0.8382 | 0.7031 |
56
- | 0.0028 | 1.05 | 1482 | 0.8482 | 0.8460 | 0.7500 |
57
- | 0.0021 | 2.05 | 2223 | 0.8839 | 0.8821 | 0.5604 |
58
- | 0.0002 | 3.05 | 2964 | 0.9018 | 0.9001 | 0.3880 |
59
- | 0.0001 | 4.05 | 3705 | 0.9286 | 0.9284 | 0.4309 |
60
- | 0.0001 | 5.05 | 4446 | 0.9107 | 0.9105 | 0.7365 |
61
- | 0.8987 | 6.05 | 5187 | 0.8393 | 0.8294 | 0.9310 |
62
- | 0.4888 | 7.05 | 5928 | 0.875 | 0.8703 | 0.8563 |
63
- | 0.0001 | 8.05 | 6669 | 0.8929 | 0.8894 | 0.6909 |
64
- | 0.0018 | 9.05 | 7410 | 0.8929 | 0.8917 | 0.9169 |
65
- | 0.0 | 10.05 | 8151 | 0.8929 | 0.8928 | 0.6104 |
66
- | 0.0 | 11.05 | 8892 | 0.9196 | 0.9207 | 0.6125 |
67
- | 0.0 | 12.05 | 9633 | 0.9286 | 0.9281 | 0.5644 |
68
- | 0.0 | 13.05 | 10374 | 0.9286 | 0.9286 | 0.5062 |
69
- | 0.0 | 14.05 | 11115 | 0.9375 | 0.9373 | 0.5186 |
70
- | 0.0 | 15.0013 | 11116 | 0.7569 | 0.9023 | 0.9016 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7609
22
+ - Accuracy: 0.9163
23
+ - F1: 0.9154
24
 
25
  ## Model description
26
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - training_steps: 22230
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|
55
+ | 0.0 | 0.0333 | 741 | 0.9082 | 0.9070 | 0.9068 |
56
+ | 0.5976 | 1.0333 | 1482 | 2.5471 | 0.7302 | 0.7286 |
57
+ | 0.1188 | 2.0333 | 2223 | 1.0145 | 0.8698 | 0.8695 |
58
+ | 0.0001 | 3.0333 | 2964 | 1.1956 | 0.8465 | 0.8384 |
59
+ | 0.5026 | 4.0333 | 3705 | 0.8190 | 0.8651 | 0.8608 |
60
+ | 0.0 | 5.0333 | 4446 | 1.1466 | 0.8372 | 0.8377 |
61
+ | 0.0 | 6.0333 | 5187 | 1.0804 | 0.8419 | 0.8358 |
62
+ | 0.0 | 7.0333 | 5928 | 0.8535 | 0.8930 | 0.8909 |
63
+ | 0.0 | 8.0333 | 6669 | 0.6512 | 0.9070 | 0.9070 |
64
+ | 0.0001 | 9.0333 | 7410 | 0.8475 | 0.8884 | 0.8887 |
65
+ | 0.0001 | 10.0333 | 8151 | 0.7335 | 0.8977 | 0.8972 |
66
+ | 0.0 | 11.0333 | 8892 | 0.7774 | 0.9070 | 0.9054 |
67
+ | 0.0 | 12.0333 | 9633 | 0.7346 | 0.9116 | 0.9107 |
68
+ | 0.0 | 13.0333 | 10374 | 0.7609 | 0.9163 | 0.9154 |
69
+ | 0.0 | 14.0333 | 11115 | 0.7560 | 0.9070 | 0.9074 |
70
+ | 0.0 | 15.0333 | 11856 | 0.8036 | 0.9163 | 0.9151 |
71
+ | 0.0 | 16.0333 | 12597 | 0.7962 | 0.9163 | 0.9151 |
72
+ | 0.0 | 17.0333 | 13338 | 0.7821 | 0.9163 | 0.9147 |
73
+ | 0.0 | 18.0333 | 14079 | 0.7898 | 0.9163 | 0.9149 |
74
+ | 0.0 | 19.0333 | 14820 | 1.0166 | 0.8791 | 0.8748 |
75
+ | 0.0 | 20.0333 | 15561 | 0.8697 | 0.8977 | 0.8968 |
76
+ | 0.0 | 21.0333 | 16302 | 0.7670 | 0.9023 | 0.9017 |
77
+ | 0.0 | 22.0333 | 17043 | 0.7399 | 0.9116 | 0.9107 |
78
+ | 0.0 | 23.0333 | 17784 | 0.7458 | 0.9116 | 0.9107 |
79
+ | 0.0 | 24.0333 | 18525 | 0.7701 | 0.8977 | 0.8969 |
80
+ | 0.0 | 25.0333 | 19266 | 0.7924 | 0.9023 | 0.9014 |
81
+ | 0.0 | 26.0333 | 20007 | 0.7955 | 0.9023 | 0.9014 |
82
+ | 0.0 | 27.0333 | 20748 | 0.8675 | 0.8977 | 0.8969 |
83
+ | 0.0 | 28.0333 | 21489 | 0.8671 | 0.8977 | 0.8969 |
84
+ | 0.0 | 29.0333 | 22230 | 0.8665 | 0.8977 | 0.8969 |
85
 
86
 
87
  ### Framework versions
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 15.001349527665317,
3
- "eval_accuracy": 0.9023255813953488,
4
- "eval_f1": 0.9016146713373171,
5
- "eval_loss": 0.756963849067688,
6
- "eval_runtime": 137.6677,
7
- "eval_samples_per_second": 1.562,
8
- "eval_steps_per_second": 1.562
9
  }
 
1
  {
2
+ "epoch": 29.033333333333335,
3
+ "eval_accuracy": 0.9162790697674419,
4
+ "eval_f1": 0.9153581572237279,
5
+ "eval_loss": 0.7608880996704102,
6
+ "eval_runtime": 142.5038,
7
+ "eval_samples_per_second": 1.509,
8
+ "eval_steps_per_second": 1.509
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:295f0bca9a8079827c2e3acf2f4e7c369676ddc0347f17f528802c947ab32045
3
  size 354621528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd2313190f24f230ed5ba7f6a988e56b4645862cccb2d9e0332491b3358f92c
3
  size 354621528
test_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 15.001349527665317,
3
  "eval_accuracy": 0.9375,
4
- "eval_f1": 0.9373365167161658,
5
- "eval_loss": 0.5185860991477966,
6
- "eval_runtime": 72.3734,
7
- "eval_samples_per_second": 1.548,
8
- "eval_steps_per_second": 1.548
9
  }
 
1
  {
2
+ "epoch": 29.033333333333335,
3
  "eval_accuracy": 0.9375,
4
+ "eval_f1": 0.9386944198366612,
5
+ "eval_loss": 0.5316240191459656,
6
+ "eval_runtime": 76.8207,
7
+ "eval_samples_per_second": 1.458,
8
+ "eval_steps_per_second": 1.458
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
val_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 15.001349527665317,
3
- "eval_accuracy": 0.9023255813953488,
4
- "eval_f1": 0.9016146713373171,
5
- "eval_loss": 0.756963849067688,
6
- "eval_runtime": 137.6677,
7
- "eval_samples_per_second": 1.562,
8
- "eval_steps_per_second": 1.562
9
  }
 
1
  {
2
+ "epoch": 29.033333333333335,
3
+ "eval_accuracy": 0.9162790697674419,
4
+ "eval_f1": 0.9153581572237279,
5
+ "eval_loss": 0.7608880996704102,
6
+ "eval_runtime": 142.5038,
7
+ "eval_samples_per_second": 1.509,
8
+ "eval_steps_per_second": 1.509
9
  }