Hugging Face's logo

Temo27Anas
/
tsf-newDS-r224-f90-8.8-h768-i3072-p32-b8-e50

Safetensors
timesformer
Generated from Trainer
Model card Files Community
Temo27Anas commited on
Commit
aafbfb2
·
verified ·
1 Parent(s): 40c8a60

Model save

Browse files
Files changed (2) hide show
  1. README.md +111 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/timesformer-base-finetuned-k400
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: tsf-newDS-r224-f90-8.8-h768-i3072-p32-b8-e50
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
+ # tsf-newDS-r224-f90-8.8-h768-i3072-p32-b8-e50
17
+
18
+ This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.9773
21
+ - Accuracy: 0.8186
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - training_steps: 6550
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.1214 | 0.02 | 131 | 1.1007 | 0.3319 |
55
+ | 1.135 | 1.02 | 262 | 1.1006 | 0.3496 |
56
+ | 1.1075 | 2.02 | 393 | 1.1293 | 0.3230 |
57
+ | 1.157 | 3.02 | 524 | 1.1034 | 0.3540 |
58
+ | 1.1213 | 4.02 | 655 | 1.2115 | 0.3230 |
59
+ | 1.1139 | 5.02 | 786 | 1.0907 | 0.3540 |
60
+ | 1.1237 | 6.02 | 917 | 1.0917 | 0.3230 |
61
+ | 1.1137 | 7.02 | 1048 | 1.1317 | 0.3230 |
62
+ | 1.1056 | 8.02 | 1179 | 1.1004 | 0.3319 |
63
+ | 1.1082 | 9.02 | 1310 | 1.1200 | 0.3142 |
64
+ | 1.0915 | 10.02 | 1441 | 1.0995 | 0.3982 |
65
+ | 1.0066 | 11.02 | 1572 | 1.0283 | 0.4602 |
66
+ | 0.9384 | 12.02 | 1703 | 1.0246 | 0.4690 |
67
+ | 0.991 | 13.02 | 1834 | 1.0044 | 0.4513 |
68
+ | 0.9787 | 14.02 | 1965 | 0.9504 | 0.5442 |
69
+ | 0.8522 | 15.02 | 2096 | 0.8761 | 0.6195 |
70
+ | 0.9404 | 16.02 | 2227 | 0.9207 | 0.5531 |
71
+ | 0.8297 | 17.02 | 2358 | 0.9401 | 0.6018 |
72
+ | 0.6493 | 18.02 | 2489 | 0.8470 | 0.6283 |
73
+ | 0.6117 | 19.02 | 2620 | 0.9770 | 0.6283 |
74
+ | 0.676 | 20.02 | 2751 | 0.9361 | 0.6504 |
75
+ | 0.5106 | 21.02 | 2882 | 0.7691 | 0.6947 |
76
+ | 0.5782 | 22.02 | 3013 | 0.6593 | 0.7832 |
77
+ | 0.5183 | 23.02 | 3144 | 0.9417 | 0.6770 |
78
+ | 0.4466 | 24.02 | 3275 | 0.7373 | 0.7257 |
79
+ | 0.7414 | 25.02 | 3406 | 0.7389 | 0.7788 |
80
+ | 0.6338 | 26.02 | 3537 | 0.6562 | 0.7788 |
81
+ | 0.5423 | 27.02 | 3668 | 0.4732 | 0.8540 |
82
+ | 0.6629 | 28.02 | 3799 | 0.9399 | 0.7434 |
83
+ | 0.3087 | 29.02 | 3930 | 1.0425 | 0.6947 |
84
+ | 0.2584 | 30.02 | 4061 | 0.6969 | 0.7965 |
85
+ | 0.2846 | 31.02 | 4192 | 0.6573 | 0.8186 |
86
+ | 0.4084 | 32.02 | 4323 | 0.6418 | 0.8053 |
87
+ | 0.4092 | 33.02 | 4454 | 1.1458 | 0.7434 |
88
+ | 0.4956 | 34.02 | 4585 | 0.8430 | 0.8053 |
89
+ | 0.28 | 35.02 | 4716 | 0.7289 | 0.8009 |
90
+ | 0.2646 | 36.02 | 4847 | 0.6761 | 0.8053 |
91
+ | 0.313 | 37.02 | 4978 | 1.0661 | 0.7832 |
92
+ | 0.2937 | 38.02 | 5109 | 0.9224 | 0.8009 |
93
+ | 0.2626 | 39.02 | 5240 | 0.5193 | 0.8628 |
94
+ | 0.4277 | 40.02 | 5371 | 0.6577 | 0.8319 |
95
+ | 0.1663 | 41.02 | 5502 | 1.1011 | 0.7743 |
96
+ | 0.1576 | 42.02 | 5633 | 0.7574 | 0.8407 |
97
+ | 0.3203 | 43.02 | 5764 | 0.8206 | 0.8407 |
98
+ | 0.2027 | 44.02 | 5895 | 1.1296 | 0.7743 |
99
+ | 0.188 | 45.02 | 6026 | 0.9082 | 0.8009 |
100
+ | 0.1701 | 46.02 | 6157 | 1.0158 | 0.8009 |
101
+ | 0.2083 | 47.02 | 6288 | 1.1480 | 0.7788 |
102
+ | 0.1618 | 48.02 | 6419 | 0.9984 | 0.8009 |
103
+ | 0.2421 | 49.02 | 6550 | 0.9773 | 0.8186 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.41.2
109
+ - Pytorch 1.13.0+cu117
110
+ - Datasets 2.20.0
111
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f82181dc65488a751b9004acc0d7ea7f592e772934e97ff7984d8fc4ce81ce39
3
  size 324974092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec06646da76d00c5a5894f323915cbe5817e18660dc0a204d437ca7727aafc10
3
  size 324974092