Hugging Face's logo

be2be2
/
koelectra_emotion_v2

Text Classification
Transformers
Safetensors
electra
Generated from Trainer
Model card Files
xet
Community
be2be2 commited on
Commit
21de2da
·
verified ·
1 Parent(s): b643ba3

be2be2/koelectra_emotion_v2

Browse files
Files changed (4) hide show
  1. README.md +24 -14
  2. config.json +14 -14
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [monologg/koelectra-small-finetuned-sentiment](https://huggingface.co/monologg/koelectra-small-finetuned-sentiment) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.9556
22
- - Accuracy: 0.6876
23
- - F1: 0.6854
24
 
25
  ## Model description
26
 
@@ -45,22 +45,32 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - num_epochs: 10
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
54
- | 1.2179 | 1.0 | 1466 | 0.9643 | 0.6553 | 0.6470 |
55
- | 0.9217 | 2.0 | 2932 | 0.8961 | 0.6749 | 0.6701 |
56
- | 0.8429 | 3.0 | 4398 | 0.8783 | 0.6882 | 0.6808 |
57
- | 0.7853 | 4.0 | 5864 | 0.8862 | 0.6876 | 0.6835 |
58
- | 0.7381 | 5.0 | 7330 | 0.8941 | 0.6867 | 0.6812 |
59
- | 0.6967 | 6.0 | 8796 | 0.9089 | 0.6884 | 0.6821 |
60
- | 0.6581 | 7.0 | 10262 | 0.9189 | 0.6869 | 0.6839 |
61
- | 0.6306 | 8.0 | 11728 | 0.9284 | 0.6876 | 0.6853 |
62
- | 0.6059 | 9.0 | 13194 | 0.9519 | 0.6876 | 0.6840 |
63
- | 0.5879 | 10.0 | 14660 | 0.9556 | 0.6876 | 0.6854 |
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [monologg/koelectra-small-finetuned-sentiment](https://huggingface.co/monologg/koelectra-small-finetuned-sentiment) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.4260
22
+ - Accuracy: 0.6118
23
+ - F1: 0.6172
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 20
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
54
+ | 1.5444 | 1.0 | 601 | 1.3725 | 0.4626 | 0.4567 |
55
+ | 1.218 | 2.0 | 1202 | 1.2090 | 0.5664 | 0.5693 |
56
+ | 1.0556 | 3.0 | 1803 | 1.1186 | 0.6031 | 0.6075 |
57
+ | 0.9497 | 4.0 | 2404 | 1.1470 | 0.5981 | 0.6056 |
58
+ | 0.8734 | 5.0 | 3005 | 1.1450 | 0.6005 | 0.6067 |
59
+ | 0.808 | 6.0 | 3606 | 1.1479 | 0.6136 | 0.6181 |
60
+ | 0.7489 | 7.0 | 4207 | 1.1225 | 0.6287 | 0.6348 |
61
+ | 0.6926 | 8.0 | 4808 | 1.2075 | 0.6096 | 0.6177 |
62
+ | 0.6472 | 9.0 | 5409 | 1.2047 | 0.6180 | 0.6227 |
63
+ | 0.6028 | 10.0 | 6010 | 1.2248 | 0.6194 | 0.6249 |
64
+ | 0.5624 | 11.0 | 6611 | 1.2474 | 0.6154 | 0.6215 |
65
+ | 0.5303 | 12.0 | 7212 | 1.2627 | 0.6203 | 0.6257 |
66
+ | 0.4956 | 13.0 | 7813 | 1.2977 | 0.6191 | 0.6245 |
67
+ | 0.4662 | 14.0 | 8414 | 1.3655 | 0.6081 | 0.6144 |
68
+ | 0.4439 | 15.0 | 9015 | 1.3801 | 0.6067 | 0.6124 |
69
+ | 0.4221 | 16.0 | 9616 | 1.3854 | 0.6124 | 0.6167 |
70
+ | 0.4097 | 17.0 | 10217 | 1.4101 | 0.6105 | 0.6164 |
71
+ | 0.3921 | 18.0 | 10818 | 1.4359 | 0.6054 | 0.6109 |
72
+ | 0.3799 | 19.0 | 11419 | 1.4269 | 0.6111 | 0.6169 |
73
+ | 0.369 | 20.0 | 12020 | 1.4260 | 0.6118 | 0.6172 |
74
 
75
 
76
  ### Framework versions
config.json CHANGED
@@ -11,24 +11,24 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 256,
13
  "id2label": {
14
- "0": "\ubd88\uc548",
15
- "1": "\ubd84\ub178",
16
- "2": "\uc2ac\ud514",
17
- "3": "\uc911\ub9bd",
18
- "4": "\ud589\ubcf5",
19
- "5": "\ud610\uc624",
20
- "6": "\ub2f9\ud669"
21
  },
22
  "initializer_range": 0.02,
23
  "intermediate_size": 1024,
24
  "label2id": {
25
- "\ub2f9\ud669": 6,
26
- "\ubd84\ub178": 1,
27
- "\ubd88\uc548": 0,
28
- "\uc2ac\ud514": 2,
29
- "\uc911\ub9bd": 3,
30
- "\ud589\ubcf5": 4,
31
- "\ud610\uc624": 5
32
  },
33
  "layer_norm_eps": 1e-12,
34
  "max_position_embeddings": 512,
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 256,
13
  "id2label": {
14
+ "0": "\ubd84\ub178",
15
+ "1": "\uc2ac\ud514",
16
+ "2": "\uc911\ub9bd",
17
+ "3": "\ud610\uc624",
18
+ "4": "\ub2f9\ud669",
19
+ "5": "\ubd88\uc548",
20
+ "6": "\ud589\ubcf5"
21
  },
22
  "initializer_range": 0.02,
23
  "intermediate_size": 1024,
24
  "label2id": {
25
+ "\ub2f9\ud669": 4,
26
+ "\ubd84\ub178": 0,
27
+ "\ubd88\uc548": 5,
28
+ "\uc2ac\ud514": 1,
29
+ "\uc911\ub9bd": 2,
30
+ "\ud589\ubcf5": 6,
31
+ "\ud610\uc624": 3
32
  },
33
  "layer_norm_eps": 1e-12,
34
  "max_position_embeddings": 512,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e5164b41b8f2af89b0f2ee88773282cb56e6ca122b33e4b057236b27414a70f
3
  size 55085476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f83250eaa3942067c36d4d2b7db6febbaf80530c28ff507dde27284455df917
3
  size 55085476
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:424e078537cc0dbcfd1e23873d60d7124ff49445bb99193c652b1427c54a8f3f
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2cf98367aa3eb9cf0f0958ed3e31eef09f04ce0cd165ccf420d8f36f6fe36b9
3
  size 5777