Hugging Face's logo

whoisjones
/
finerweb-binary-classifier-mdeberta-4o

Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
Model card Files
xet
Community
whoisjones commited on
Commit
aeb8880
·
verified ·
1 Parent(s): 8515857

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -64
README.md CHANGED
@@ -9,22 +9,18 @@ metrics:
9
  - recall
10
  - accuracy
11
  model-index:
12
- - name: openai-fineweb-edu-scorer-mdeberta-binary-lr5e-05-20250411_132948
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # openai-fineweb-edu-scorer-mdeberta-binary-lr5e-05-20250411_132948
20
 
21
  This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.1606
24
- - Precision: 1.0
25
- - Recall: 1.0
26
- - F1 Macro: 1.0
27
- - Accuracy: 1.0
28
 
29
  ## Model description
30
 
@@ -51,64 +47,6 @@ The following hyperparameters were used during training:
51
  - lr_scheduler_type: linear
52
  - num_epochs: 20
53
 
54
- ### Training results
55
-
56
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
57
- |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:--------:|:--------:|
58
- | No log | 0 | 0 | 0.3573 | 1.0 | 1.0 | 1.0 | 1.0 |
59
- | 0.1215 | 0.3908 | 1000 | 0.1103 | 1.0 | 1.0 | 1.0 | 1.0 |
60
- | 0.1107 | 0.7816 | 2000 | 0.1143 | 1.0 | 1.0 | 1.0 | 1.0 |
61
- | 0.0892 | 1.1723 | 3000 | 0.1120 | 1.0 | 1.0 | 1.0 | 1.0 |
62
- | 0.0893 | 1.5631 | 4000 | 0.1125 | 1.0 | 1.0 | 1.0 | 1.0 |
63
- | 0.0888 | 1.9539 | 5000 | 0.1101 | 1.0 | 1.0 | 1.0 | 1.0 |
64
- | 0.0433 | 2.3447 | 6000 | 0.1286 | 1.0 | 1.0 | 1.0 | 1.0 |
65
- | 0.0524 | 2.7354 | 7000 | 0.1353 | 1.0 | 1.0 | 1.0 | 1.0 |
66
- | 0.0302 | 3.1262 | 8000 | 0.1432 | 1.0 | 1.0 | 1.0 | 1.0 |
67
- | 0.0344 | 3.5170 | 9000 | 0.1357 | 1.0 | 1.0 | 1.0 | 1.0 |
68
- | 0.0331 | 3.9078 | 10000 | 0.1378 | 1.0 | 1.0 | 1.0 | 1.0 |
69
- | 0.0227 | 4.2986 | 11000 | 0.1442 | 1.0 | 1.0 | 1.0 | 1.0 |
70
- | 0.0211 | 4.6893 | 12000 | 0.1437 | 1.0 | 1.0 | 1.0 | 1.0 |
71
- | 0.0184 | 5.0801 | 13000 | 0.1472 | 1.0 | 1.0 | 1.0 | 1.0 |
72
- | 0.0188 | 5.4709 | 14000 | 0.1452 | 1.0 | 1.0 | 1.0 | 1.0 |
73
- | 0.0238 | 5.8617 | 15000 | 0.1410 | 1.0 | 1.0 | 1.0 | 1.0 |
74
- | 0.0142 | 6.2524 | 16000 | 0.1488 | 1.0 | 1.0 | 1.0 | 1.0 |
75
- | 0.0125 | 6.6432 | 17000 | 0.1568 | 1.0 | 1.0 | 1.0 | 1.0 |
76
- | 0.0119 | 7.0340 | 18000 | 0.1507 | 1.0 | 1.0 | 1.0 | 1.0 |
77
- | 0.0177 | 7.4248 | 19000 | 0.1593 | 1.0 | 1.0 | 1.0 | 1.0 |
78
- | 0.0136 | 7.8156 | 20000 | 0.1544 | 1.0 | 1.0 | 1.0 | 1.0 |
79
- | 0.0118 | 8.2063 | 21000 | 0.1641 | 1.0 | 1.0 | 1.0 | 1.0 |
80
- | 0.0152 | 8.5971 | 22000 | 0.1524 | 1.0 | 1.0 | 1.0 | 1.0 |
81
- | 0.0113 | 8.9879 | 23000 | 0.1554 | 1.0 | 1.0 | 1.0 | 1.0 |
82
- | 0.0114 | 9.3787 | 24000 | 0.1482 | 1.0 | 1.0 | 1.0 | 1.0 |
83
- | 0.0121 | 9.7694 | 25000 | 0.1451 | 1.0 | 1.0 | 1.0 | 1.0 |
84
- | 0.0089 | 10.1602 | 26000 | 0.1561 | 1.0 | 1.0 | 1.0 | 1.0 |
85
- | 0.0087 | 10.5510 | 27000 | 0.1621 | 1.0 | 1.0 | 1.0 | 1.0 |
86
- | 0.0114 | 10.9418 | 28000 | 0.1553 | 1.0 | 1.0 | 1.0 | 1.0 |
87
- | 0.0061 | 11.3326 | 29000 | 0.1547 | 1.0 | 1.0 | 1.0 | 1.0 |
88
- | 0.0075 | 11.7233 | 30000 | 0.1578 | 1.0 | 1.0 | 1.0 | 1.0 |
89
- | 0.0063 | 12.1141 | 31000 | 0.1575 | 1.0 | 1.0 | 1.0 | 1.0 |
90
- | 0.0081 | 12.5049 | 32000 | 0.1587 | 1.0 | 1.0 | 1.0 | 1.0 |
91
- | 0.0088 | 12.8957 | 33000 | 0.1592 | 1.0 | 1.0 | 1.0 | 1.0 |
92
- | 0.0062 | 13.2864 | 34000 | 0.1614 | 1.0 | 1.0 | 1.0 | 1.0 |
93
- | 0.0085 | 13.6772 | 35000 | 0.1563 | 1.0 | 1.0 | 1.0 | 1.0 |
94
- | 0.0056 | 14.0680 | 36000 | 0.1585 | 1.0 | 1.0 | 1.0 | 1.0 |
95
- | 0.0046 | 14.4588 | 37000 | 0.1608 | 1.0 | 1.0 | 1.0 | 1.0 |
96
- | 0.0066 | 14.8496 | 38000 | 0.1697 | 1.0 | 1.0 | 1.0 | 1.0 |
97
- | 0.0068 | 15.2403 | 39000 | 0.1570 | 1.0 | 1.0 | 1.0 | 1.0 |
98
- | 0.0046 | 15.6311 | 40000 | 0.1745 | 1.0 | 1.0 | 1.0 | 1.0 |
99
- | 0.0062 | 16.0219 | 41000 | 0.1617 | 1.0 | 1.0 | 1.0 | 1.0 |
100
- | 0.0056 | 16.4127 | 42000 | 0.1653 | 1.0 | 1.0 | 1.0 | 1.0 |
101
- | 0.0053 | 16.8034 | 43000 | 0.1551 | 1.0 | 1.0 | 1.0 | 1.0 |
102
- | 0.0026 | 17.1942 | 44000 | 0.1638 | 1.0 | 1.0 | 1.0 | 1.0 |
103
- | 0.005 | 17.5850 | 45000 | 0.1555 | 1.0 | 1.0 | 1.0 | 1.0 |
104
- | 0.0033 | 17.9758 | 46000 | 0.1577 | 1.0 | 1.0 | 1.0 | 1.0 |
105
- | 0.0049 | 18.3665 | 47000 | 0.1545 | 1.0 | 1.0 | 1.0 | 1.0 |
106
- | 0.0043 | 18.7573 | 48000 | 0.1589 | 1.0 | 1.0 | 1.0 | 1.0 |
107
- | 0.0046 | 19.1481 | 49000 | 0.1588 | 1.0 | 1.0 | 1.0 | 1.0 |
108
- | 0.0047 | 19.5389 | 50000 | 0.1596 | 1.0 | 1.0 | 1.0 | 1.0 |
109
- | 0.0041 | 19.9297 | 51000 | 0.1606 | 1.0 | 1.0 | 1.0 | 1.0 |
110
-
111
-
112
  ### Framework versions
113
 
114
  - Transformers 4.49.0
 
9
  - recall
10
  - accuracy
11
  model-index:
12
+ - name: finerweb-binary-classifier-mdeberta-4o
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # finerweb-binary-classifier-mdeberta-4o
20
 
21
  This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.1606
 
 
 
 
24
 
25
  ## Model description
26
 
 
47
  - lr_scheduler_type: linear
48
  - num_epochs: 20
49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  ### Framework versions
51
 
52
  - Transformers 4.49.0