Hugging Face's logo

Shijia
/
run1

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Community
Shijia commited on
Commit
3730b80
•
1 Parent(s): 3877d2e

Model save

Browse files
Files changed (2) hide show
  1. README.md +30 -40
  2. generation_config.json +6 -0
README.md CHANGED
@@ -1,20 +1,18 @@
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
@@ -22,18 +20,9 @@ model-index:
22
  split: validation
23
  args: sem_eval_2024_task_2_source
24
  metrics:
25
- - name: Accuracy
26
- type: accuracy
27
- value: 0.505
28
- - name: Precision
29
- type: precision
30
- value: 0.5122819945959224
31
- - name: Recall
32
- type: recall
33
- value: 0.505
34
- - name: F1
35
- type: f1
36
- value: 0.41886061459892576
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,13 +30,14 @@ 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: 0.6932
47
- - Accuracy: 0.505
48
- - Precision: 0.5123
49
- - Recall: 0.505
50
- - F1: 0.4189
 
51
 
52
  ## Model description
53
 
@@ -67,11 +57,11 @@ More information needed
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: 10
@@ -79,18 +69,18 @@ The following hyperparameters were used during training:
79
 
80
  ### Training results
81
 
82
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
83
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
84
- | No log | 0.99 | 53 | 0.6942 | 0.5 | 0.5 | 0.5 | 0.3420 |
85
- | 0.6934 | 2.0 | 107 | 0.6931 | 0.505 | 0.5072 | 0.505 | 0.4645 |
86
- | 0.6934 | 2.99 | 160 | 0.6945 | 0.5 | 0.25 | 0.5 | 0.3333 |
87
- | 0.6946 | 4.0 | 214 | 0.6933 | 0.495 | 0.4944 | 0.495 | 0.4809 |
88
- | 0.6946 | 4.99 | 267 | 0.6961 | 0.5 | 0.25 | 0.5 | 0.3333 |
89
- | 0.6949 | 6.0 | 321 | 0.6935 | 0.5 | 0.25 | 0.5 | 0.3333 |
90
- | 0.6949 | 6.99 | 374 | 0.6931 | 0.505 | 0.5070 | 0.505 | 0.4676 |
91
- | 0.6941 | 8.0 | 428 | 0.6933 | 0.495 | 0.2487 | 0.495 | 0.3311 |
92
- | 0.6941 | 8.99 | 481 | 0.6930 | 0.51 | 0.5106 | 0.51 | 0.5028 |
93
- | 0.692 | 9.91 | 530 | 0.6932 | 0.505 | 0.5123 | 0.505 | 0.4189 |
94
 
95
 
96
  ### Framework versions
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: google/flan-t5-base
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
  - sem_eval_2024_task_2
8
  metrics:
9
+ - rouge
 
 
 
10
  model-index:
11
  - name: run1
12
  results:
13
  - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
  dataset:
17
  name: sem_eval_2024_task_2
18
  type: sem_eval_2024_task_2
 
20
  split: validation
21
  args: sem_eval_2024_task_2_source
22
  metrics:
23
+ - name: Rouge1
24
+ type: rouge
25
+ value: 52.0
 
 
 
 
 
 
 
 
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # run1
32
 
33
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the sem_eval_2024_task_2 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: nan
36
+ - Rouge1: 52.0
37
+ - Rouge2: 0.0
38
+ - Rougel: 52.0
39
+ - Rougelsum: 52.0
40
+ - Gen Len: 3.0
41
 
42
  ## Model description
43
 
 
57
 
58
  The following hyperparameters were used during training:
59
  - learning_rate: 2e-05
60
+ - train_batch_size: 4
61
+ - eval_batch_size: 16
62
  - seed: 42
63
  - gradient_accumulation_steps: 2
64
+ - total_train_batch_size: 8
65
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
  - lr_scheduler_type: linear
67
  - num_epochs: 10
 
69
 
70
  ### Training results
71
 
72
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
73
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
74
+ | No log | 1.0 | 212 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
75
+ | 0.0 | 2.0 | 425 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
76
+ | 0.0 | 3.0 | 637 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
77
+ | 0.0 | 4.0 | 850 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
78
+ | 0.0 | 5.0 | 1062 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
79
+ | 0.0 | 6.0 | 1275 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
80
+ | 0.0 | 7.0 | 1487 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
81
+ | 0.0 | 8.0 | 1700 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
82
+ | 0.0 | 9.0 | 1912 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
83
+ | 0.0 | 9.98 | 2120 | nan | 52.0 | 0.0 | 52.0 | 52.0 | 3.0 |
84
 
85
 
86
  ### Framework versions
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.35.2"
6
+ }