add model

.gitignore

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

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- spearmanr
+model-index:
+- name: koelectra-sts-v0.4
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.9286505242442783
+---
+
+<!-- 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-v0.4
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3368
+- Pearson: 0.9303
+- Spearmanr: 0.9287
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
+| 0.0345        | 1.0   | 730  | 0.3368          | 0.9303  | 0.9287    |
+| 0.0343        | 2.0   | 1460 | 0.3368          | 0.9303  | 0.9287    |
+| 0.0337        | 3.0   | 2190 | 0.3368          | 0.9303  | 0.9287    |
+| 0.0345        | 4.0   | 2920 | 0.3368          | 0.9303  | 0.9287    |
+| 0.0347        | 5.0   | 3650 | 0.3368          | 0.9303  | 0.9287    |
+
+
+### 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-v0.3/checkpoint-7560",
+  "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 sha256:21822f34855cc24298e12fc0208f4e013cfd2af01b540ad8554507d2c3d2deef
+size 451773805

runs/Dec29_23-28-20_DESKTOP-QEJTC97/1640816935.7341359/events.out.tfevents.1640816935.DESKTOP-QEJTC97.16524.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15302ab6d27f3e4e5f135bc3840e7decfad0107bcbf7f21a5f9c949fac144961
+size 4218

runs/Dec29_23-28-20_DESKTOP-QEJTC97/1640818824.9027493/events.out.tfevents.1640818824.DESKTOP-QEJTC97.16524.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06ff6fdb86da714143319af68ff5c3789cd0023c607f3d742a5ca00e9590e46
+size 4218

runs/Dec29_23-28-20_DESKTOP-QEJTC97/events.out.tfevents.1640816935.DESKTOP-QEJTC97.16524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4557ac7758579037b44127979348e1349557aebeb9234e2865a3a7995928cf
+size 6571

runs/Dec29_23-28-20_DESKTOP-QEJTC97/events.out.tfevents.1640818741.DESKTOP-QEJTC97.16524.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b6b6814beea4a0191528827d05dd1f48a3ee793ba13a024b25cc92b339d131
+size 415

runs/Dec29_23-28-20_DESKTOP-QEJTC97/events.out.tfevents.1640818824.DESKTOP-QEJTC97.16524.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3029a7965fbe30377e97f06d87c4e9b91cf4ee8e96b69644ab07ed09e9bd8e46
+size 6571

runs/Dec29_23-28-20_DESKTOP-QEJTC97/events.out.tfevents.1640820655.DESKTOP-QEJTC97.16524.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb0cf75a0305e2858753b75e868782d4aeeac70f7f6749c9bba9b845a0923d5
+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-v0.3/checkpoint-7560", "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:e3bb9863e423c9fc0cb861ca5cdc430eb8d19f09f344ea51995ad8132991c18d
+size 2671