Training complete
Browse files
README.md
CHANGED
@@ -24,16 +24,16 @@ model-index:
|
|
24 |
metrics:
|
25 |
- name: Precision
|
26 |
type: precision
|
27 |
-
value: 0.
|
28 |
- name: Recall
|
29 |
type: recall
|
30 |
-
value: 0.
|
31 |
- name: F1
|
32 |
type: f1
|
33 |
-
value: 0.
|
34 |
- name: Accuracy
|
35 |
type: accuracy
|
36 |
-
value: 0.
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
43 |
|
44 |
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the conll2002 dataset.
|
45 |
It achieves the following results on the evaluation set:
|
46 |
-
- Loss: 0.
|
47 |
-
- Precision: 0.
|
48 |
-
- Recall: 0.
|
49 |
-
- F1: 0.
|
50 |
-
- Accuracy: 0.
|
51 |
|
52 |
## Model description
|
53 |
|
@@ -72,19 +72,27 @@ The following hyperparameters were used during training:
|
|
72 |
- seed: 42
|
73 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
- lr_scheduler_type: linear
|
75 |
-
- num_epochs:
|
76 |
|
77 |
### Training results
|
78 |
|
79 |
-
| Training Loss | Epoch | Step
|
80 |
-
|
81 |
-
| 0.
|
82 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
|
84 |
|
85 |
### Framework versions
|
86 |
|
87 |
- Transformers 4.41.1
|
88 |
- Pytorch 2.3.0+cu121
|
89 |
-
- Datasets 2.19.
|
90 |
- Tokenizers 0.19.1
|
|
|
24 |
metrics:
|
25 |
- name: Precision
|
26 |
type: precision
|
27 |
+
value: 0.7494539100043687
|
28 |
- name: Recall
|
29 |
type: recall
|
30 |
+
value: 0.7883731617647058
|
31 |
- name: F1
|
32 |
type: f1
|
33 |
+
value: 0.7684210526315789
|
34 |
- name: Accuracy
|
35 |
type: accuracy
|
36 |
+
value: 0.9629927984937011
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
43 |
|
44 |
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the conll2002 dataset.
|
45 |
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.2531
|
47 |
+
- Precision: 0.7495
|
48 |
+
- Recall: 0.7884
|
49 |
+
- F1: 0.7684
|
50 |
+
- Accuracy: 0.9630
|
51 |
|
52 |
## Model description
|
53 |
|
|
|
72 |
- seed: 42
|
73 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
- lr_scheduler_type: linear
|
75 |
+
- num_epochs: 10
|
76 |
|
77 |
### Training results
|
78 |
|
79 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
+
| 0.1214 | 1.0 | 1041 | 0.1681 | 0.6611 | 0.6997 | 0.6798 | 0.9523 |
|
82 |
+
| 0.0814 | 2.0 | 2082 | 0.1652 | 0.6692 | 0.7270 | 0.6969 | 0.9540 |
|
83 |
+
| 0.0531 | 3.0 | 3123 | 0.1628 | 0.7291 | 0.7682 | 0.7481 | 0.9624 |
|
84 |
+
| 0.0357 | 4.0 | 4164 | 0.1799 | 0.7427 | 0.7721 | 0.7571 | 0.9620 |
|
85 |
+
| 0.0277 | 5.0 | 5205 | 0.1963 | 0.7530 | 0.7824 | 0.7674 | 0.9627 |
|
86 |
+
| 0.0168 | 6.0 | 6246 | 0.2115 | 0.7333 | 0.7771 | 0.7546 | 0.9615 |
|
87 |
+
| 0.0136 | 7.0 | 7287 | 0.2311 | 0.7376 | 0.7769 | 0.7567 | 0.9613 |
|
88 |
+
| 0.0106 | 8.0 | 8328 | 0.2450 | 0.7552 | 0.7861 | 0.7703 | 0.9626 |
|
89 |
+
| 0.0062 | 9.0 | 9369 | 0.2572 | 0.7589 | 0.7877 | 0.7730 | 0.9622 |
|
90 |
+
| 0.0061 | 10.0 | 10410 | 0.2531 | 0.7495 | 0.7884 | 0.7684 | 0.9630 |
|
91 |
|
92 |
|
93 |
### Framework versions
|
94 |
|
95 |
- Transformers 4.41.1
|
96 |
- Pytorch 2.3.0+cu121
|
97 |
+
- Datasets 2.19.2
|
98 |
- Tokenizers 0.19.1
|