add model

.gitignore

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

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- spearmanr
+model-index:
+- name: koelectra-sts-v0.6
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.8711267002878285
+---
+
+<!-- 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-v0.6
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0065
+- Pearson: 0.9988
+- Spearmanr: 0.8711
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:---------:|
+| 0.045         | 1.0   | 12500 | 0.0186          | 0.9963  | 0.8703    |
+| 0.0173        | 2.0   | 25000 | 0.0338          | 0.9930  | 0.8693    |
+| 0.0133        | 3.0   | 37500 | 0.0100          | 0.9980  | 0.8709    |
+| 0.0101        | 4.0   | 50000 | 0.0065          | 0.9988  | 0.8711    |
+| 0.01          | 5.0   | 62500 | 0.0064          | 0.9987  | 0.8711    |
+
+
+### 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-v0.5/checkpoint-31250",
+  "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 sha256:331beb808cdf8c9695502dcf5042fc9da98d4bc12d6dad0567c1fa7858c3ce85
+size 451773805

runs/Mar20_12-10-55_DESKTOP-QEJTC97/1647774667.864169/events.out.tfevents.1647774667.DESKTOP-QEJTC97.6852.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e3e8711bfeb30e1f62c30e3233d83bac5ca32be7f7759dc10297337fdf2d04
+size 4218

runs/Mar20_12-10-55_DESKTOP-QEJTC97/events.out.tfevents.1647774667.DESKTOP-QEJTC97.6852.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7aeb57e9647b3fae58b3d215aadfcdf1326ce823dd695387b3c93b139283c8a
+size 25411

runs/Mar20_12-10-55_DESKTOP-QEJTC97/events.out.tfevents.1647794929.DESKTOP-QEJTC97.6852.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab097a37dc457bc9935353ec2fff077eebf289f215692461e4c9318ead719dbb
+size 422

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-v0.5/checkpoint-31250", "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 sha256:45fe8f2f064e3937188f2ac58c2aac55f532c005d50a17c888c64b219a0e59fa
+size 2671