Hugging Face's logo

addykan
/
model_data

Text Classification
Transformers
TensorBoard
Safetensors
canine
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
addykan commited on
Commit
64b7bab
•
1 Parent(s): cad22ab

End of training

Browse files
Files changed (2) hide show
  1. README.md +8 -31
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/canine-c](https://huggingface.co/google/canine-c) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.0986
21
- - Accuracy: 0.3333
22
 
23
  ## Model description
24
 
@@ -37,43 +37,20 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.002
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
- - num_epochs: 25
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
- |:-------------:|:-----:|:------:|:---------------:|:--------:|
52
- | 1.1073 | 1.0 | 6000 | 1.1015 | 0.3333 |
53
- | 1.1022 | 2.0 | 12000 | 1.1043 | 0.3333 |
54
- | 1.103 | 3.0 | 18000 | 1.1026 | 0.3333 |
55
- | 1.101 | 4.0 | 24000 | 1.1163 | 0.3333 |
56
- | 1.1027 | 5.0 | 30000 | 1.0987 | 0.3333 |
57
- | 1.1026 | 6.0 | 36000 | 1.0988 | 0.3333 |
58
- | 1.1039 | 7.0 | 42000 | 1.0998 | 0.3333 |
59
- | 1.1045 | 8.0 | 48000 | 1.1015 | 0.3333 |
60
- | 1.1026 | 9.0 | 54000 | 1.1206 | 0.3333 |
61
- | 1.1035 | 10.0 | 60000 | 1.1042 | 0.3333 |
62
- | 1.1027 | 11.0 | 66000 | 1.0989 | 0.3333 |
63
- | 1.1011 | 12.0 | 72000 | 1.1176 | 0.3333 |
64
- | 1.1015 | 13.0 | 78000 | 1.0994 | 0.3333 |
65
- | 1.1025 | 14.0 | 84000 | 1.0993 | 0.3333 |
66
- | 1.1007 | 15.0 | 90000 | 1.1004 | 0.3333 |
67
- | 1.101 | 16.0 | 96000 | 1.1016 | 0.3333 |
68
- | 1.0999 | 17.0 | 102000 | 1.1028 | 0.3333 |
69
- | 1.1003 | 18.0 | 108000 | 1.0988 | 0.3333 |
70
- | 1.0986 | 19.0 | 114000 | 1.0989 | 0.3333 |
71
- | 1.0999 | 20.0 | 120000 | 1.0987 | 0.3333 |
72
- | 1.0997 | 21.0 | 126000 | 1.0989 | 0.3333 |
73
- | 1.0992 | 22.0 | 132000 | 1.0990 | 0.3333 |
74
- | 1.0991 | 23.0 | 138000 | 1.0986 | 0.3333 |
75
- | 1.0989 | 24.0 | 144000 | 1.0986 | 0.3333 |
76
- | 1.0984 | 25.0 | 150000 | 1.0986 | 0.3333 |
77
 
78
 
79
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/canine-c](https://huggingface.co/google/canine-c) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0010
21
+ - Accuracy: 0.9999
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2e-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
+ - num_epochs: 2
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 0.0134 | 1.0 | 6000 | 0.0009 | 0.9999 |
53
+ | 0.0 | 2.0 | 12000 | 0.0010 | 0.9999 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321ceef96138cfe52acc4a00c3b582baf49fe094eb08ebdcbd5d9b372af370fb
3
  size 528371004
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ab8a2f90eca78424dc4ffe9115242bce4de8b914125352fa11ca19d33f5181
3
  size 528371004