harr commited on
Commit
69b4374
1 Parent(s): 84fb29d
README.md CHANGED
@@ -22,16 +22,16 @@ model-index:
22
  metrics:
23
  - name: Precision
24
  type: precision
25
- value: 0.9847619047619047
26
  - name: Recall
27
  type: recall
28
- value: 0.988527724665392
29
  - name: F1
30
  type: f1
31
- value: 0.9866412213740458
32
  - name: Accuracy
33
  type: accuracy
34
- value: 0.9974453590689754
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ingredients_yes_no dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.0138
45
- - Precision: 0.9848
46
- - Recall: 0.9885
47
- - F1: 0.9866
48
- - Accuracy: 0.9974
49
 
50
  ## Model description
51
 
@@ -76,21 +76,21 @@ The following hyperparameters were used during training:
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
- | No log | 1.0 | 83 | 0.1004 | 0.8978 | 0.9235 | 0.9105 | 0.9807 |
80
- | No log | 2.0 | 166 | 0.0237 | 0.9714 | 0.9751 | 0.9733 | 0.9940 |
81
- | No log | 3.0 | 249 | 0.0204 | 0.9715 | 0.9771 | 0.9743 | 0.9929 |
82
- | No log | 4.0 | 332 | 0.0138 | 0.9773 | 0.9866 | 0.9819 | 0.9969 |
83
- | No log | 5.0 | 415 | 0.0137 | 0.9829 | 0.9866 | 0.9847 | 0.9969 |
84
- | No log | 6.0 | 498 | 0.0134 | 0.9847 | 0.9866 | 0.9857 | 0.9972 |
85
- | 0.0923 | 7.0 | 581 | 0.0160 | 0.9866 | 0.9885 | 0.9876 | 0.9972 |
86
- | 0.0923 | 8.0 | 664 | 0.0147 | 0.9848 | 0.9885 | 0.9866 | 0.9974 |
87
- | 0.0923 | 9.0 | 747 | 0.0139 | 0.9848 | 0.9885 | 0.9866 | 0.9974 |
88
- | 0.0923 | 10.0 | 830 | 0.0138 | 0.9848 | 0.9885 | 0.9866 | 0.9974 |
89
 
90
 
91
  ### Framework versions
92
 
93
- - Transformers 4.10.0
94
  - Pytorch 1.9.0+cu102
95
  - Datasets 1.11.0
96
  - Tokenizers 0.10.3
 
22
  metrics:
23
  - name: Precision
24
  type: precision
25
+ value: 0.9865319865319865
26
  - name: Recall
27
  type: recall
28
+ value: 0.9932203389830508
29
  - name: F1
30
  type: f1
31
+ value: 0.9898648648648648
32
  - name: Accuracy
33
  type: accuracy
34
+ value: 0.9972885032537961
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ingredients_yes_no dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.0100
45
+ - Precision: 0.9865
46
+ - Recall: 0.9932
47
+ - F1: 0.9899
48
+ - Accuracy: 0.9973
49
 
50
  ## Model description
51
 
 
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | No log | 1.0 | 47 | 0.2822 | 0.4075 | 0.5525 | 0.4691 | 0.8932 |
80
+ | No log | 2.0 | 94 | 0.0972 | 0.8429 | 0.8915 | 0.8666 | 0.9783 |
81
+ | No log | 3.0 | 141 | 0.0223 | 0.9865 | 0.9932 | 0.9899 | 0.9973 |
82
+ | No log | 4.0 | 188 | 0.0170 | 0.9798 | 0.9864 | 0.9831 | 0.9962 |
83
+ | No log | 5.0 | 235 | 0.0136 | 0.9865 | 0.9932 | 0.9899 | 0.9973 |
84
+ | No log | 6.0 | 282 | 0.0124 | 0.9865 | 0.9932 | 0.9899 | 0.9973 |
85
+ | No log | 7.0 | 329 | 0.0121 | 0.9865 | 0.9932 | 0.9899 | 0.9973 |
86
+ | No log | 8.0 | 376 | 0.0118 | 0.9865 | 0.9932 | 0.9899 | 0.9973 |
87
+ | No log | 9.0 | 423 | 0.0107 | 0.9865 | 0.9932 | 0.9899 | 0.9973 |
88
+ | No log | 10.0 | 470 | 0.0100 | 0.9865 | 0.9932 | 0.9899 | 0.9973 |
89
 
90
 
91
  ### Framework versions
92
 
93
+ - Transformers 4.10.2
94
  - Pytorch 1.9.0+cu102
95
  - Datasets 1.11.0
96
  - Tokenizers 0.10.3
config.json CHANGED
@@ -33,6 +33,6 @@
33
  "sinusoidal_pos_embds": false,
34
  "tie_weights_": true,
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.10.0",
37
  "vocab_size": 30522
38
  }
 
33
  "sinusoidal_pos_embds": false,
34
  "tie_weights_": true,
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.10.2",
37
  "vocab_size": 30522
38
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cac3fd8d49080c0db3d1a12df616e2207ca61d2cc49a3a0c4caf3c140a558d9
3
  size 265506293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306b7e418f8b69bd3c48af64e40254f52629dfb03b1620b258e5bb03d9d380f0
3
  size 265506293
runs/Sep11_08-25-51_99a39cb50201/1631348875.950971/events.out.tfevents.1631348875.99a39cb50201.75.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72893cdaf2c62c8354a3225fc8dc1271fbd079e4e863d9a112706bd71349cfd3
3
+ size 4230
runs/Sep11_08-25-51_99a39cb50201/events.out.tfevents.1631348875.99a39cb50201.75.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bd55326d895900f56b1e10c119e331f59b5ec0bce4023106053bcce09bb8b6
3
+ size 8138
runs/Sep11_08-25-51_99a39cb50201/events.out.tfevents.1631348936.99a39cb50201.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100eb9d60435b37809ab765f19cb2e89b090a15c8272f2474f11dbc7fb3d4380
3
+ size 512
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdc59e0b95ad2a399ec0786f027476dc9f2a790cc1f16f7ee53df949e2f99e04
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d77f6fbd8e01267c1ce606943de338451560d29d2bbf2f44eb1c637fb4c66fa
3
  size 2671