Model save
Browse files- README.md +111 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: medicalai/ClinicalBERT
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- sem_eval_2024_task_2
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
model-index:
|
13 |
+
- name: run1
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: sem_eval_2024_task_2
|
20 |
+
type: sem_eval_2024_task_2
|
21 |
+
config: sem_eval_2024_task_2_source
|
22 |
+
split: validation
|
23 |
+
args: sem_eval_2024_task_2_source
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.595
|
28 |
+
- name: Precision
|
29 |
+
type: precision
|
30 |
+
value: 0.632109581421221
|
31 |
+
- name: Recall
|
32 |
+
type: recall
|
33 |
+
value: 0.595
|
34 |
+
- name: F1
|
35 |
+
type: f1
|
36 |
+
value: 0.5644107445349681
|
37 |
+
---
|
38 |
+
|
39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
+
should probably proofread and complete it, then remove this comment. -->
|
41 |
+
|
42 |
+
# run1
|
43 |
+
|
44 |
+
This model is a fine-tuned version of [medicalai/ClinicalBERT](https://huggingface.co/medicalai/ClinicalBERT) on the sem_eval_2024_task_2 dataset.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.6989
|
47 |
+
- Accuracy: 0.595
|
48 |
+
- Precision: 0.6321
|
49 |
+
- Recall: 0.595
|
50 |
+
- F1: 0.5644
|
51 |
+
|
52 |
+
## Model description
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Intended uses & limitations
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training and evaluation data
|
61 |
+
|
62 |
+
More information needed
|
63 |
+
|
64 |
+
## Training procedure
|
65 |
+
|
66 |
+
### Training hyperparameters
|
67 |
+
|
68 |
+
The following hyperparameters were used during training:
|
69 |
+
- learning_rate: 2e-05
|
70 |
+
- train_batch_size: 16
|
71 |
+
- eval_batch_size: 64
|
72 |
+
- seed: 42
|
73 |
+
- gradient_accumulation_steps: 2
|
74 |
+
- total_train_batch_size: 32
|
75 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
76 |
+
- lr_scheduler_type: linear
|
77 |
+
- num_epochs: 20
|
78 |
+
- mixed_precision_training: Native AMP
|
79 |
+
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
83 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
84 |
+
| No log | 0.99 | 53 | 0.6932 | 0.5 | 0.5 | 0.5 | 0.4302 |
|
85 |
+
| 0.6952 | 2.0 | 107 | 0.6946 | 0.505 | 0.5059 | 0.505 | 0.4854 |
|
86 |
+
| 0.6952 | 2.99 | 160 | 0.6938 | 0.485 | 0.4127 | 0.485 | 0.3505 |
|
87 |
+
| 0.6953 | 4.0 | 214 | 0.6937 | 0.5 | 0.5 | 0.5 | 0.4389 |
|
88 |
+
| 0.6953 | 4.99 | 267 | 0.6961 | 0.5 | 0.25 | 0.5 | 0.3333 |
|
89 |
+
| 0.6937 | 6.0 | 321 | 0.6936 | 0.5 | 0.25 | 0.5 | 0.3333 |
|
90 |
+
| 0.6937 | 6.99 | 374 | 0.6908 | 0.495 | 0.4487 | 0.495 | 0.3479 |
|
91 |
+
| 0.6927 | 8.0 | 428 | 0.6804 | 0.545 | 0.5485 | 0.545 | 0.5366 |
|
92 |
+
| 0.6927 | 8.99 | 481 | 0.6888 | 0.525 | 0.5535 | 0.525 | 0.4520 |
|
93 |
+
| 0.6799 | 10.0 | 535 | 0.6657 | 0.615 | 0.6476 | 0.615 | 0.5925 |
|
94 |
+
| 0.6799 | 10.99 | 588 | 0.6600 | 0.625 | 0.6448 | 0.625 | 0.6117 |
|
95 |
+
| 0.6509 | 12.0 | 642 | 0.6598 | 0.595 | 0.6407 | 0.595 | 0.5592 |
|
96 |
+
| 0.6509 | 12.99 | 695 | 0.6598 | 0.605 | 0.6555 | 0.605 | 0.5701 |
|
97 |
+
| 0.6122 | 14.0 | 749 | 0.6643 | 0.59 | 0.6234 | 0.59 | 0.5603 |
|
98 |
+
| 0.6122 | 14.99 | 802 | 0.6754 | 0.605 | 0.6818 | 0.605 | 0.5584 |
|
99 |
+
| 0.5601 | 16.0 | 856 | 0.6788 | 0.605 | 0.6382 | 0.605 | 0.5798 |
|
100 |
+
| 0.5601 | 16.99 | 909 | 0.6864 | 0.59 | 0.6234 | 0.59 | 0.5603 |
|
101 |
+
| 0.5159 | 18.0 | 963 | 0.6967 | 0.6 | 0.6457 | 0.6 | 0.5660 |
|
102 |
+
| 0.5159 | 18.99 | 1016 | 0.7037 | 0.6 | 0.6507 | 0.6 | 0.5633 |
|
103 |
+
| 0.5117 | 19.81 | 1060 | 0.6989 | 0.595 | 0.6321 | 0.595 | 0.5644 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.35.2
|
109 |
+
- Pytorch 2.1.0+cu121
|
110 |
+
- Datasets 2.15.0
|
111 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 541317368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6cadef33911d1a16c26d2d953053ed7bea60e4a4f23bd9a948aac00c1ce4f71
|
3 |
size 541317368
|