Hugging Face's logo

Ketzu
/
koelectra-sts-v0.6

Text Classification
Transformers
PyTorch
TensorBoard
electra
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
Ketzu commited on
Commit
7a58290
•
1 Parent(s): 20cd4b1

add model

Browse files
Files changed (8) hide show
  1. README.md +11 -11
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. runs/Mar21_10-52-40_DESKTOP-QEJTC97/1647856369.519228/events.out.tfevents.1647856369.DESKTOP-QEJTC97.15564.1 +3 -0
  5. runs/Mar21_10-52-40_DESKTOP-QEJTC97/events.out.tfevents.1647856369.DESKTOP-QEJTC97.15564.0 +3 -0
  6. runs/Mar21_10-52-40_DESKTOP-QEJTC97/events.out.tfevents.1647897716.DESKTOP-QEJTC97.15564.2 +3 -0
  7. tokenizer_config.json +1 -1
  8. training_args.bin +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ model-index:
12
  metrics:
13
  - name: Spearmanr
14
  type: spearmanr
15
- value: 0.8711267002878285
16
  ---
17
 
18
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,9 +22,9 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model was trained from scratch on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.0065
26
- - Pearson: 0.9988
27
- - Spearmanr: 0.8711
28
 
29
  ## Model description
30
 
@@ -53,13 +53,13 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
57
- |:-------------:|:-----:|:-----:|:---------------:|:-------:|:---------:|
58
- | 0.045 | 1.0 | 12500 | 0.0186 | 0.9963 | 0.8703 |
59
- | 0.0173 | 2.0 | 25000 | 0.0338 | 0.9930 | 0.8693 |
60
- | 0.0133 | 3.0 | 37500 | 0.0100 | 0.9980 | 0.8709 |
61
- | 0.0101 | 4.0 | 50000 | 0.0065 | 0.9988 | 0.8711 |
62
- | 0.01 | 5.0 | 62500 | 0.0064 | 0.9987 | 0.8711 |
63
 
64
 
65
  ### Framework versions
 
12
  metrics:
13
  - name: Spearmanr
14
  type: spearmanr
15
+ value: 0.8728969637834377
16
  ---
17
 
18
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
22
 
23
  This model was trained from scratch on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 0.0008
26
+ - Pearson: 0.9999
27
+ - Spearmanr: 0.8729
28
 
29
  ## Model description
30
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
57
+ |:-------------:|:-----:|:------:|:---------------:|:-------:|:---------:|
58
+ | 0.0285 | 1.0 | 25000 | 0.0040 | 0.9992 | 0.8727 |
59
+ | 0.0193 | 2.0 | 50000 | 0.0119 | 0.9976 | 0.8722 |
60
+ | 0.0069 | 3.0 | 75000 | 0.0036 | 0.9993 | 0.8727 |
61
+ | 0.006 | 4.0 | 100000 | 0.0012 | 0.9998 | 0.8729 |
62
+ | 0.0034 | 5.0 | 125000 | 0.0008 | 0.9999 | 0.8729 |
63
 
64
 
65
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./koelectra-sts-v0.5/checkpoint-31250",
3
  "architectures": [
4
  "ElectraForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "./koelectra-sts-v0.6/checkpoint-62500",
3
  "architectures": [
4
  "ElectraForSequenceClassification"
5
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:331beb808cdf8c9695502dcf5042fc9da98d4bc12d6dad0567c1fa7858c3ce85
3
  size 451773805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c510e072c3a26c12eef63832e018424616abea4afce9167f135577dfefba5b9
3
  size 451773805
runs/Mar21_10-52-40_DESKTOP-QEJTC97/1647856369.519228/events.out.tfevents.1647856369.DESKTOP-QEJTC97.15564.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a5f85e5b838ea90df98c990fc12669c87e4fd675ca3384ca4f21aa8379c2cff
3
+ size 4218
runs/Mar21_10-52-40_DESKTOP-QEJTC97/events.out.tfevents.1647856369.DESKTOP-QEJTC97.15564.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec81bfcd6a6fe2bf82786bac052269e0b4ca835d022807e738829663dd34854
3
+ size 45418
runs/Mar21_10-52-40_DESKTOP-QEJTC97/events.out.tfevents.1647897716.DESKTOP-QEJTC97.15564.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29056fe6be2d2f6e343241060ece1f71fa76e75966ed166836c2d64ad3fa940
3
+ size 422
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./koelectra-sts-v0.5/checkpoint-31250", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./koelectra-sts-v0.6/checkpoint-62500", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45fe8f2f064e3937188f2ac58c2aac55f532c005d50a17c888c64b219a0e59fa
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6986538d575a407dfb9ab4372c8c945548390a3c8eb506986475562c6152103
3
  size 2671