judithrosell commited on
Commit
12403f8
1 Parent(s): bffa389

End of training

Browse files
Files changed (1) hide show
  1. README.md +36 -36
README.md CHANGED
@@ -14,18 +14,18 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.1433
18
  - Seqeval classification report: precision recall f1-score support
19
 
20
- DNA 0.81 0.83 0.82 1593
21
- RNA 0.79 0.83 0.81 1400
22
- cell_line 0.77 0.82 0.79 1016
23
- cell_type 0.98 0.96 0.97 37439
24
- protein 0.85 0.86 0.85 2992
25
 
26
- micro avg 0.95 0.94 0.95 44440
27
- macro avg 0.84 0.86 0.85 44440
28
- weighted avg 0.95 0.94 0.95 44440
29
 
30
 
31
  ## Model description
@@ -59,41 +59,41 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Seqeval classification report |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
62
- | 0.2673 | 1.0 | 582 | 0.1492 | precision recall f1-score support
63
 
64
- DNA 0.79 0.81 0.80 1593
65
- RNA 0.78 0.79 0.79 1400
66
- cell_line 0.74 0.84 0.79 1016
67
- cell_type 0.98 0.96 0.97 37439
68
- protein 0.84 0.86 0.85 2992
69
 
70
- micro avg 0.95 0.94 0.94 44440
71
- macro avg 0.83 0.85 0.84 44440
72
- weighted avg 0.95 0.94 0.94 44440
73
  |
74
- | 0.1408 | 2.0 | 1164 | 0.1469 | precision recall f1-score support
75
 
76
- DNA 0.83 0.80 0.81 1593
77
- RNA 0.78 0.83 0.80 1400
78
- cell_line 0.75 0.83 0.79 1016
79
- cell_type 0.98 0.96 0.97 37439
80
- protein 0.84 0.87 0.85 2992
81
 
82
- micro avg 0.95 0.94 0.95 44440
83
- macro avg 0.84 0.86 0.85 44440
84
- weighted avg 0.95 0.94 0.95 44440
85
  |
86
- | 0.1237 | 3.0 | 1746 | 0.1433 | precision recall f1-score support
87
 
88
- DNA 0.81 0.83 0.82 1593
89
- RNA 0.79 0.83 0.81 1400
90
- cell_line 0.77 0.82 0.79 1016
91
- cell_type 0.98 0.96 0.97 37439
92
- protein 0.85 0.86 0.85 2992
93
 
94
- micro avg 0.95 0.94 0.95 44440
95
- macro avg 0.84 0.86 0.85 44440
96
- weighted avg 0.95 0.94 0.95 44440
97
  |
98
 
99
 
 
14
 
15
  This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.1445
18
  - Seqeval classification report: precision recall f1-score support
19
 
20
+ DNA 0.72 0.80 0.76 507
21
+ RNA 0.81 0.83 0.82 1593
22
+ cell_line 0.76 0.78 0.77 5750
23
+ cell_type 0.76 0.81 0.79 618
24
+ protein 0.81 0.81 0.81 1452
25
 
26
+ micro avg 0.77 0.80 0.78 9920
27
+ macro avg 0.77 0.81 0.79 9920
28
+ weighted avg 0.77 0.80 0.78 9920
29
 
30
 
31
  ## Model description
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Seqeval classification report |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
62
+ | 0.2687 | 1.0 | 582 | 0.1504 | precision recall f1-score support
63
 
64
+ DNA 0.72 0.81 0.76 507
65
+ RNA 0.78 0.82 0.80 1593
66
+ cell_line 0.75 0.77 0.76 5750
67
+ cell_type 0.76 0.81 0.78 618
68
+ protein 0.80 0.81 0.80 1452
69
 
70
+ micro avg 0.76 0.79 0.77 9920
71
+ macro avg 0.76 0.80 0.78 9920
72
+ weighted avg 0.76 0.79 0.77 9920
73
  |
74
+ | 0.1412 | 2.0 | 1164 | 0.1461 | precision recall f1-score support
75
 
76
+ DNA 0.72 0.81 0.76 507
77
+ RNA 0.83 0.79 0.81 1593
78
+ cell_line 0.75 0.77 0.76 5750
79
+ cell_type 0.75 0.82 0.78 618
80
+ protein 0.85 0.75 0.80 1452
81
 
82
+ micro avg 0.78 0.78 0.78 9920
83
+ macro avg 0.78 0.79 0.78 9920
84
+ weighted avg 0.78 0.78 0.78 9920
85
  |
86
+ | 0.1251 | 3.0 | 1746 | 0.1445 | precision recall f1-score support
87
 
88
+ DNA 0.72 0.80 0.76 507
89
+ RNA 0.81 0.83 0.82 1593
90
+ cell_line 0.76 0.78 0.77 5750
91
+ cell_type 0.76 0.81 0.79 618
92
+ protein 0.81 0.81 0.81 1452
93
 
94
+ micro avg 0.77 0.80 0.78 9920
95
+ macro avg 0.77 0.81 0.79 9920
96
+ weighted avg 0.77 0.80 0.78 9920
97
  |
98
 
99