yeonju52 commited on
Commit
ea1b8ef
1 Parent(s): 63e4f84

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: F1
23
  type: f1
24
- value: 0.4168211999760723
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on the klue dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.2087
35
- - F1: 0.4168
36
 
37
  ## Model description
38
 
@@ -51,9 +51,9 @@ More information needed
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
- - learning_rate: 5e-05
55
- - train_batch_size: 24
56
- - eval_batch_size: 24
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
@@ -63,9 +63,9 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | F1 |
65
  |:-------------:|:-----:|:----:|:---------------:|:------:|
66
- | 0.255 | 1.0 | 876 | 0.2267 | 0.3606 |
67
- | 0.1677 | 2.0 | 1752 | 0.2111 | 0.4045 |
68
- | 0.1234 | 3.0 | 2628 | 0.2087 | 0.4168 |
69
 
70
 
71
  ### Framework versions
 
21
  metrics:
22
  - name: F1
23
  type: f1
24
+ value: 0.41368436709802175
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on the klue dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.1969
35
+ - F1: 0.4137
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 2e-05
55
+ - train_batch_size: 30
56
+ - eval_batch_size: 30
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | F1 |
65
  |:-------------:|:-----:|:----:|:---------------:|:------:|
66
+ | No log | 1.0 | 701 | 0.2158 | 0.3687 |
67
+ | 0.2387 | 2.0 | 1402 | 0.2007 | 0.4061 |
68
+ | 0.1552 | 3.0 | 2103 | 0.1969 | 0.4137 |
69
 
70
 
71
  ### Framework versions