solikang/koelectra-small-v3-nsmc

README.md

@@ -0,0 +1,91 @@
+---
+base_model: monologg/koelectra-small-v3-discriminator
+tags:
+- generated_from_trainer
+datasets:
+- generator
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: chkpt
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: generator
+      type: generator
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8869565217391304
+    - name: F1
+      type: f1
+      value: 0.8338208775796434
+    - name: Precision
+      type: precision
+      value: 0.7866918714555766
+    - name: Recall
+      type: recall
+      value: 0.8869565217391304
+---
+
+<!-- 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. -->
+
+# chkpt
+
+This model is a fine-tuned version of [monologg/koelectra-small-v3-discriminator](https://huggingface.co/monologg/koelectra-small-v3-discriminator) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2041
+- Accuracy: 0.8870
+- F1: 0.8338
+- Precision: 0.7867
+- Recall: 0.8870
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Accuracy | F1     | Validation Loss | Precision | Recall |
+|:-------------:|:-----:|:----:|:--------:|:------:|:---------------:|:---------:|:------:|
+| No log        | 1.0   | 12   | 0.8280   | 0.7500 | 1.4560          | 0.6855    | 0.8280 |
+| No log        | 2.0   | 24   | 0.9140   | 0.8729 | 1.2494          | 0.8354    | 0.9140 |
+| No log        | 1.0   | 29   | 0.9304   | 0.8969 | 1.1763          | 0.8657    | 0.9304 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "monologg/koelectra-small-v3-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "BUY",
+    "1": "HOLD",
+    "2": "NOT RATED",
+    "3": "OUTPERFORM",
+    "4": "TRADING BUY"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "BUY": "0",
+    "HOLD": "1",
+    "NOT RATED": "2",
+    "OUTPERFORM": "3",
+    "TRADING BUY": "4"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 35000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a026b23db07bdf6fa579d09593b199415e48e7c51e1e005f83205ec8a859a0
+size 56517020

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa0799d8b2f0c0eeffb023c4e2774b55bffd027264cec69b6800947e94bb362
+size 4472