add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- spearmanr
+model-index:
+- name: koelectra-sts-v0.5
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.8718027458578232
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# koelectra-sts-v0.5
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0216
+- Pearson: 0.9961
+- Spearmanr: 0.8718
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
+| 0.2535        | 1.0   | 1250 | 0.1680          | 0.9662  | 0.8601    |
+| 0.0888        | 2.0   | 2500 | 0.0462          | 0.9909  | 0.8679    |
+| 0.049         | 3.0   | 3750 | 0.0704          | 0.9862  | 0.8676    |
+| 0.0266        | 4.0   | 5000 | 0.0223          | 0.9959  | 0.8718    |
+| 0.0211        | 5.0   | 6250 | 0.0216          | 0.9961  | 0.8718    |
+
+
+### Framework versions
+
+- Transformers 4.10.0
+- Pytorch 1.10.1+cu113
+- Datasets 1.17.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "./koelectra-sts-v0.4/checkpoint-3650",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0",
+  "type_vocab_size": 2,
+  "vocab_size": 35000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372615979a6059005723cf48ee4e59766bf818ce23c4347da50dde5908591c1d
+size 451773805

runs/Mar19_14-07-30_DESKTOP-QEJTC97/1647695300.7420425/events.out.tfevents.1647695300.DESKTOP-QEJTC97.2516.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c24ceacc2d53063170ba5d52c2ff44d771cd46c17b7afe020da617a0dcf371d
+size 4218

runs/Mar19_14-07-30_DESKTOP-QEJTC97/events.out.tfevents.1647695300.DESKTOP-QEJTC97.2516.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd777cbaa6c685a0a262db9c005e2129bc09fed5cef7de2b8f83f20b7e80223
+size 3400

runs/Mar19_14-12-42_DESKTOP-QEJTC97/1647695573.0711825/events.out.tfevents.1647695573.DESKTOP-QEJTC97.2516.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e6998271ecde217aa9a7b68c6a970e0e6ab56ad8396cc9ca92f61dfde5f75c
+size 4218

runs/Mar19_14-12-42_DESKTOP-QEJTC97/events.out.tfevents.1647695573.DESKTOP-QEJTC97.2516.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006be012ad5c13928b73141833cec896c387cdb9f0681fba5359449f6eace7b8
+size 3243

runs/Mar19_14-14-00_DESKTOP-QEJTC97/1647695698.0543327/events.out.tfevents.1647695698.DESKTOP-QEJTC97.2516.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6de6b466953017d006bbd10dab5608dbe83625bea1928835c9259fae35f0772
+size 4218

runs/Mar19_14-14-00_DESKTOP-QEJTC97/events.out.tfevents.1647695698.DESKTOP-QEJTC97.2516.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce12ffb514fff690dafc8590fe7d60b7f95901e64b657e29ccdf327a1c399c61
+size 7356

runs/Mar19_14-14-00_DESKTOP-QEJTC97/events.out.tfevents.1647705967.DESKTOP-QEJTC97.2516.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1fca80a4d78b67e2752531c33fbd0846c1154f0613c4143d52400d1f3f42a15
+size 415

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9151d19bfaabe640527753a28b97b4845a6d00447f61c9f59b126891c8b61b3a
+size 2671