Ketzu commited on
Commit
bcd45b9
1 Parent(s): d2693ab
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - spearmanr
6
+ model-index:
7
+ - name: koelectra-sts-v0.5
8
+ results:
9
+ - task:
10
+ name: Text Classification
11
+ type: text-classification
12
+ metrics:
13
+ - name: Spearmanr
14
+ type: spearmanr
15
+ value: 0.8718027458578232
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # koelectra-sts-v0.5
22
+
23
+ This model was trained from scratch on an unknown dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 0.0216
26
+ - Pearson: 0.9961
27
+ - Spearmanr: 0.8718
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 5
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
57
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
58
+ | 0.2535 | 1.0 | 1250 | 0.1680 | 0.9662 | 0.8601 |
59
+ | 0.0888 | 2.0 | 2500 | 0.0462 | 0.9909 | 0.8679 |
60
+ | 0.049 | 3.0 | 3750 | 0.0704 | 0.9862 | 0.8676 |
61
+ | 0.0266 | 4.0 | 5000 | 0.0223 | 0.9959 | 0.8718 |
62
+ | 0.0211 | 5.0 | 6250 | 0.0216 | 0.9961 | 0.8718 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.10.0
68
+ - Pytorch 1.10.1+cu113
69
+ - Datasets 1.17.0
70
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./koelectra-sts-v0.4/checkpoint-3650",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "electra",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "problem_type": "regression",
28
+ "summary_activation": "gelu",
29
+ "summary_last_dropout": 0.1,
30
+ "summary_type": "first",
31
+ "summary_use_proj": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.10.0",
34
+ "type_vocab_size": 2,
35
+ "vocab_size": 35000
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372615979a6059005723cf48ee4e59766bf818ce23c4347da50dde5908591c1d
3
+ size 451773805
runs/Mar19_14-07-30_DESKTOP-QEJTC97/1647695300.7420425/events.out.tfevents.1647695300.DESKTOP-QEJTC97.2516.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c24ceacc2d53063170ba5d52c2ff44d771cd46c17b7afe020da617a0dcf371d
3
+ size 4218
runs/Mar19_14-07-30_DESKTOP-QEJTC97/events.out.tfevents.1647695300.DESKTOP-QEJTC97.2516.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd777cbaa6c685a0a262db9c005e2129bc09fed5cef7de2b8f83f20b7e80223
3
+ size 3400
runs/Mar19_14-12-42_DESKTOP-QEJTC97/1647695573.0711825/events.out.tfevents.1647695573.DESKTOP-QEJTC97.2516.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e6998271ecde217aa9a7b68c6a970e0e6ab56ad8396cc9ca92f61dfde5f75c
3
+ size 4218
runs/Mar19_14-12-42_DESKTOP-QEJTC97/events.out.tfevents.1647695573.DESKTOP-QEJTC97.2516.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:006be012ad5c13928b73141833cec896c387cdb9f0681fba5359449f6eace7b8
3
+ size 3243
runs/Mar19_14-14-00_DESKTOP-QEJTC97/1647695698.0543327/events.out.tfevents.1647695698.DESKTOP-QEJTC97.2516.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6de6b466953017d006bbd10dab5608dbe83625bea1928835c9259fae35f0772
3
+ size 4218
runs/Mar19_14-14-00_DESKTOP-QEJTC97/events.out.tfevents.1647695698.DESKTOP-QEJTC97.2516.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce12ffb514fff690dafc8590fe7d60b7f95901e64b657e29ccdf327a1c399c61
3
+ size 7356
runs/Mar19_14-14-00_DESKTOP-QEJTC97/events.out.tfevents.1647705967.DESKTOP-QEJTC97.2516.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fca80a4d78b67e2752531c33fbd0846c1154f0613c4143d52400d1f3f42a15
3
+ size 415
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +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-v0.4/checkpoint-3650", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9151d19bfaabe640527753a28b97b4845a6d00447f61c9f59b126891c8b61b3a
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff