Hugging Face's logo

djsull
/
aha_class

TensorBoard
Safetensors
roberta
Model card Files Metrics Community
djsull commited on
Commit
2db9d62
·
verified ·
1 Parent(s): b913774

djsull/aha_class

Browse files
Files changed (6) hide show
  1. README.md +20 -13
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Sep09_07-43-30_129-146-79-76/events.out.tfevents.1725867811.129-146-79-76.2382365.0 +3 -0
  5. runs/Sep09_07-43-30_129-146-79-76/events.out.tfevents.1725868070.129-146-79-76.2382365.1 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: klue/roberta-base
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # aha_class
17
 
18
- This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0999
21
- - F1: 0.9664
22
- - Roc Auc: 0.9743
23
- - Accuracy: 0.9478
24
 
25
  ## Model description
26
 
@@ -51,13 +51,20 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
54
- | No log | 1.0 | 42 | 0.1375 | 0.9627 | 0.9741 | 0.9391 |
55
- | No log | 2.0 | 84 | 0.0999 | 0.9664 | 0.9743 | 0.9478 |
56
- | No log | 3.0 | 126 | 0.1220 | 0.9627 | 0.9741 | 0.9391 |
57
- | No log | 4.0 | 168 | 0.1148 | 0.9667 | 0.9763 | 0.9478 |
58
- | No log | 5.0 | 210 | 0.1353 | 0.9623 | 0.9721 | 0.9391 |
59
- | No log | 6.0 | 252 | 0.1092 | 0.9669 | 0.9783 | 0.9391 |
60
- | No log | 7.0 | 294 | 0.1435 | 0.9667 | 0.9763 | 0.9478 |
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
1
  ---
2
+ base_model: klue/roberta-small
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
15
 
16
  # aha_class
17
 
18
+ This model is a fine-tuned version of [klue/roberta-small](https://huggingface.co/klue/roberta-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0762
21
+ - F1: 0.9705
22
+ - Roc Auc: 0.9766
23
+ - Accuracy: 0.9565
24
 
25
  ## Model description
26
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
54
+ | No log | 1.0 | 42 | 0.1926 | 0.9218 | 0.9440 | 0.8609 |
55
+ | No log | 2.0 | 84 | 0.1140 | 0.9580 | 0.9679 | 0.9304 |
56
+ | No log | 3.0 | 126 | 0.1016 | 0.9536 | 0.9637 | 0.9217 |
57
+ | No log | 4.0 | 168 | 0.0800 | 0.9705 | 0.9766 | 0.9478 |
58
+ | No log | 5.0 | 210 | 0.0800 | 0.9661 | 0.9724 | 0.9478 |
59
+ | No log | 6.0 | 252 | 0.0817 | 0.9620 | 0.9701 | 0.9391 |
60
+ | No log | 7.0 | 294 | 0.0788 | 0.9661 | 0.9724 | 0.9478 |
61
+ | No log | 8.0 | 336 | 0.0803 | 0.9705 | 0.9766 | 0.9565 |
62
+ | No log | 9.0 | 378 | 0.0762 | 0.9705 | 0.9766 | 0.9565 |
63
+ | No log | 10.0 | 420 | 0.0837 | 0.9664 | 0.9743 | 0.9478 |
64
+ | No log | 11.0 | 462 | 0.0800 | 0.9664 | 0.9743 | 0.9478 |
65
+ | 0.0807 | 12.0 | 504 | 0.0815 | 0.9664 | 0.9743 | 0.9478 |
66
+ | 0.0807 | 13.0 | 546 | 0.0808 | 0.9664 | 0.9743 | 0.9478 |
67
+ | 0.0807 | 14.0 | 588 | 0.0816 | 0.9664 | 0.9743 | 0.9478 |
68
 
69
 
70
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "klue/roberta-base",
3
  "architectures": [
4
  "RobertaForSequenceClassification"
5
  ],
@@ -27,7 +27,7 @@
27
  "max_position_embeddings": 514,
28
  "model_type": "roberta",
29
  "num_attention_heads": 12,
30
- "num_hidden_layers": 12,
31
  "pad_token_id": 1,
32
  "position_embedding_type": "absolute",
33
  "problem_type": "multi_label_classification",
 
1
  {
2
+ "_name_or_path": "klue/roberta-small",
3
  "architectures": [
4
  "RobertaForSequenceClassification"
5
  ],
 
27
  "max_position_embeddings": 514,
28
  "model_type": "roberta",
29
  "num_attention_heads": 12,
30
+ "num_hidden_layers": 6,
31
  "pad_token_id": 1,
32
  "position_embedding_type": "absolute",
33
  "problem_type": "multi_label_classification",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caab6a41aff6c22c3b0310f0f7219ae09ca1527834c018dbafd3046b39b99ed5
3
- size 442505820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:061602a125454932c4542568e14cafa14e39b66c28f184f4c4ea7ee66aac0e8b
3
+ size 272385276
runs/Sep09_07-43-30_129-146-79-76/events.out.tfevents.1725867811.129-146-79-76.2382365.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c631460a94d3a9f588e96e2031fe66004c20b93391a2e73b449366e9600c1a6f
3
+ size 11520
runs/Sep09_07-43-30_129-146-79-76/events.out.tfevents.1725868070.129-146-79-76.2382365.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d638023d3f2badcfce48d6ad2d92d14067ec62c2b47569f4f760ccb197a45e8f
3
+ size 508
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:406a340849a6950bc22d5d399606cc105dfecea5d1fa10507481b8dbf064a273
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47683d0e0fb266c7731152f6cdce02035e4240b3858e6f4f96d6919566584e67
3
  size 5112