be2be2/koelectra_emotion_v3

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+base_model: monologg/koelectra-small-finetuned-sentiment
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: koelectra_emotion_v3
+  results: []
+---
+
+<!-- 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_emotion_v3
+
+This model is a fine-tuned version of [monologg/koelectra-small-finetuned-sentiment](https://huggingface.co/monologg/koelectra-small-finetuned-sentiment) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3440
+- Accuracy: 0.5564
+- F1: 0.5546
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
+| 1.727         | 1.0   | 895   | 1.6205          | 0.3526   | 0.3069 |
+| 1.5434        | 2.0   | 1790  | 1.4428          | 0.4406   | 0.4066 |
+| 1.4029        | 3.0   | 2685  | 1.3607          | 0.4855   | 0.4753 |
+| 1.3085        | 4.0   | 3580  | 1.3156          | 0.5088   | 0.4973 |
+| 1.241         | 5.0   | 4475  | 1.2789          | 0.5249   | 0.5194 |
+| 1.1863        | 6.0   | 5370  | 1.2742          | 0.5385   | 0.5310 |
+| 1.1408        | 7.0   | 6265  | 1.2499          | 0.5450   | 0.5388 |
+| 1.1039        | 8.0   | 7160  | 1.2570          | 0.5471   | 0.5375 |
+| 1.0666        | 9.0   | 8055  | 1.2541          | 0.5519   | 0.5476 |
+| 1.0321        | 10.0  | 8950  | 1.2498          | 0.5495   | 0.5441 |
+| 1.0015        | 11.0  | 9845  | 1.2688          | 0.5501   | 0.5483 |
+| 0.9714        | 12.0  | 10740 | 1.2720          | 0.5537   | 0.5518 |
+| 0.9444        | 13.0  | 11635 | 1.2770          | 0.5531   | 0.5500 |
+| 0.9202        | 14.0  | 12530 | 1.2830          | 0.5549   | 0.5526 |
+| 0.8979        | 15.0  | 13425 | 1.2969          | 0.5545   | 0.5505 |
+| 0.8771        | 16.0  | 14320 | 1.3264          | 0.5531   | 0.5502 |
+| 0.8593        | 17.0  | 15215 | 1.3280          | 0.5560   | 0.5545 |
+| 0.8427        | 18.0  | 16110 | 1.3377          | 0.5588   | 0.5565 |
+| 0.8322        | 19.0  | 17005 | 1.3371          | 0.5570   | 0.5545 |
+| 0.8196        | 20.0  | 17900 | 1.3440          | 0.5564   | 0.5546 |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,50 @@
+{
+  "_num_labels": 2,
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "\uc911\ub9bd",
+    "1": "\uc2ac\ud514",
+    "2": "\ubd84\ub178",
+    "3": "\ub2f9\ud669",
+    "4": "\ubd88\uc548",
+    "5": "\ud589\ubcf5",
+    "6": "\ud610\uc624"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "\ub2f9\ud669": 3,
+    "\ubd84\ub178": 2,
+    "\ubd88\uc548": 4,
+    "\uc2ac\ud514": 1,
+    "\uc911\ub9bd": 0,
+    "\ud589\ubcf5": 5,
+    "\ud610\uc624": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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,
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32200
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e6d6345805cb693228e9b9d3ffdb063c98236cbbef8c37f2eac150546206ee
+size 55085476

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 +1,59 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "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:f98701eca653a75e52a733cc3f238c39d0e6dce79e500d6a59232e9f841610ca
+size 5777