wzkariampuzha
commited on
Commit
•
58c7ed9
1
Parent(s):
064c51a
Upload 11 files
Browse files- README.md +83 -5
- all_results.json +17 -0
- eval_results.json +12 -0
- eval_results.txt +10 -0
- predict_results.txt +104 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +25 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,5 +1,83 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- epi_classify4_gard
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: results
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Text Classification
|
16 |
+
type: text-classification
|
17 |
+
dataset:
|
18 |
+
name: epi_classify4_gard
|
19 |
+
type: epi_classify4_gard
|
20 |
+
args: default
|
21 |
+
metrics:
|
22 |
+
- name: Precision
|
23 |
+
type: precision
|
24 |
+
value: 0.875
|
25 |
+
- name: Recall
|
26 |
+
type: recall
|
27 |
+
value: 0.9032258064516129
|
28 |
+
- name: F1
|
29 |
+
type: f1
|
30 |
+
value: 0.8888888888888888
|
31 |
+
- name: Accuracy
|
32 |
+
type: accuracy
|
33 |
+
value: 0.986
|
34 |
+
---
|
35 |
+
|
36 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
37 |
+
should probably proofread and complete it, then remove this comment. -->
|
38 |
+
|
39 |
+
# results
|
40 |
+
|
41 |
+
This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the epi_classify4_gard dataset.
|
42 |
+
It achieves the following results on the evaluation set:
|
43 |
+
- Loss: 0.0541
|
44 |
+
- Precision: 0.875
|
45 |
+
- Recall: 0.9032
|
46 |
+
- F1: 0.8889
|
47 |
+
- Accuracy: 0.986
|
48 |
+
|
49 |
+
## Model description
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Intended uses & limitations
|
54 |
+
|
55 |
+
More information needed
|
56 |
+
|
57 |
+
## Training and evaluation data
|
58 |
+
|
59 |
+
More information needed
|
60 |
+
|
61 |
+
## Training procedure
|
62 |
+
|
63 |
+
### Training hyperparameters
|
64 |
+
|
65 |
+
The following hyperparameters were used during training:
|
66 |
+
- learning_rate: 3e-05
|
67 |
+
- train_batch_size: 16
|
68 |
+
- eval_batch_size: 8
|
69 |
+
- seed: 2
|
70 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
71 |
+
- lr_scheduler_type: linear
|
72 |
+
- num_epochs: 4.0
|
73 |
+
|
74 |
+
### Training results
|
75 |
+
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.12.5
|
81 |
+
- Pytorch 1.9.0+cu102
|
82 |
+
- Datasets 1.12.1
|
83 |
+
- Tokenizers 0.10.3
|
all_results.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.986,
|
4 |
+
"eval_f1": 0.8888888888888888,
|
5 |
+
"eval_loss": 0.05408545956015587,
|
6 |
+
"eval_precision": 0.875,
|
7 |
+
"eval_recall": 0.9032258064516129,
|
8 |
+
"eval_runtime": 5.1836,
|
9 |
+
"eval_samples": 500,
|
10 |
+
"eval_samples_per_second": 96.457,
|
11 |
+
"eval_steps_per_second": 12.154,
|
12 |
+
"train_loss": 0.06538131501939562,
|
13 |
+
"train_runtime": 127.4981,
|
14 |
+
"train_samples": 1000,
|
15 |
+
"train_samples_per_second": 31.373,
|
16 |
+
"train_steps_per_second": 1.976
|
17 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.986,
|
4 |
+
"eval_f1": 0.8888888888888888,
|
5 |
+
"eval_loss": 0.05408545956015587,
|
6 |
+
"eval_precision": 0.875,
|
7 |
+
"eval_recall": 0.9032258064516129,
|
8 |
+
"eval_runtime": 5.1836,
|
9 |
+
"eval_samples": 500,
|
10 |
+
"eval_samples_per_second": 96.457,
|
11 |
+
"eval_steps_per_second": 12.154
|
12 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.05408545956015587
|
2 |
+
eval_precision = 0.875
|
3 |
+
eval_recall = 0.9032258064516129
|
4 |
+
eval_f1 = 0.8888888888888888
|
5 |
+
eval_accuracy = 0.986
|
6 |
+
eval_runtime = 5.1836
|
7 |
+
eval_samples_per_second = 96.457
|
8 |
+
eval_steps_per_second = 12.154
|
9 |
+
epoch = 4.0
|
10 |
+
eval_samples = 500
|
predict_results.txt
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
precision = 1.0
|
2 |
+
recall = 0.6
|
3 |
+
f1 = 0.7499999999999999
|
4 |
+
accuracy = 0.8163265306122449
|
5 |
+
|
6 |
+
index prediction
|
7 |
+
0 0
|
8 |
+
1 0
|
9 |
+
2 0
|
10 |
+
3 1
|
11 |
+
4 0
|
12 |
+
5 0
|
13 |
+
6 0
|
14 |
+
7 1
|
15 |
+
8 1
|
16 |
+
9 0
|
17 |
+
10 0
|
18 |
+
11 1
|
19 |
+
12 0
|
20 |
+
13 0
|
21 |
+
14 1
|
22 |
+
15 0
|
23 |
+
16 0
|
24 |
+
17 0
|
25 |
+
18 0
|
26 |
+
19 0
|
27 |
+
20 0
|
28 |
+
21 0
|
29 |
+
22 0
|
30 |
+
23 1
|
31 |
+
24 0
|
32 |
+
25 0
|
33 |
+
26 0
|
34 |
+
27 1
|
35 |
+
28 0
|
36 |
+
29 0
|
37 |
+
30 1
|
38 |
+
31 0
|
39 |
+
32 0
|
40 |
+
33 0
|
41 |
+
34 0
|
42 |
+
35 0
|
43 |
+
36 0
|
44 |
+
37 1
|
45 |
+
38 0
|
46 |
+
39 1
|
47 |
+
40 1
|
48 |
+
41 0
|
49 |
+
42 0
|
50 |
+
43 0
|
51 |
+
44 0
|
52 |
+
45 1
|
53 |
+
46 0
|
54 |
+
47 0
|
55 |
+
48 0
|
56 |
+
49 0
|
57 |
+
50 0
|
58 |
+
51 0
|
59 |
+
52 0
|
60 |
+
53 0
|
61 |
+
54 0
|
62 |
+
55 0
|
63 |
+
56 0
|
64 |
+
57 1
|
65 |
+
58 0
|
66 |
+
59 1
|
67 |
+
60 1
|
68 |
+
61 1
|
69 |
+
62 0
|
70 |
+
63 0
|
71 |
+
64 0
|
72 |
+
65 0
|
73 |
+
66 0
|
74 |
+
67 1
|
75 |
+
68 1
|
76 |
+
69 0
|
77 |
+
70 1
|
78 |
+
71 0
|
79 |
+
72 0
|
80 |
+
73 1
|
81 |
+
74 0
|
82 |
+
75 0
|
83 |
+
76 0
|
84 |
+
77 0
|
85 |
+
78 0
|
86 |
+
79 1
|
87 |
+
80 1
|
88 |
+
81 0
|
89 |
+
82 0
|
90 |
+
83 0
|
91 |
+
84 1
|
92 |
+
85 0
|
93 |
+
86 0
|
94 |
+
87 0
|
95 |
+
88 1
|
96 |
+
89 0
|
97 |
+
90 0
|
98 |
+
91 0
|
99 |
+
92 0
|
100 |
+
93 0
|
101 |
+
94 0
|
102 |
+
95 1
|
103 |
+
96 1
|
104 |
+
97 1
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "dmis-lab/biobert-base-cased-v1.2", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.06538131501939562,
|
4 |
+
"train_runtime": 127.4981,
|
5 |
+
"train_samples": 1000,
|
6 |
+
"train_samples_per_second": 31.373,
|
7 |
+
"train_steps_per_second": 1.976
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 252,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 4.0,
|
12 |
+
"step": 252,
|
13 |
+
"total_flos": 1014634340562720.0,
|
14 |
+
"train_loss": 0.06538131501939562,
|
15 |
+
"train_runtime": 127.4981,
|
16 |
+
"train_samples_per_second": 31.373,
|
17 |
+
"train_steps_per_second": 1.976
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"max_steps": 252,
|
21 |
+
"num_train_epochs": 4,
|
22 |
+
"total_flos": 1014634340562720.0,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|