pepper/roberta-base-unfair-classification

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+base_model: klue/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-unfair
+  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. -->
+
+# roberta-unfair
+
+This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1969
+- Accuracy: 0.9679
+- F1 Macro: 0.9620
+- Precision Macro: 0.9559
+- Recall Macro: 0.9688
+- Recall Unfair: 0.9710
+
+## 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: 20
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | Recall Unfair |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-------------:|
+| 0.1406        | 0.4237 | 200  | 0.2180          | 0.9390   | 0.9284   | 0.9197          | 0.9389       | 0.9384        |
+| 0.11          | 0.8475 | 400  | 0.1185          | 0.9690   | 0.9632   | 0.9582          | 0.9685       | 0.9674        |
+| 0.044         | 1.2712 | 600  | 0.1787          | 0.9615   | 0.9544   | 0.9484          | 0.9611       | 0.9601        |
+| 0.0487        | 1.6949 | 800  | 0.1957          | 0.9583   | 0.9507   | 0.9437          | 0.9588       | 0.9601        |
+| 0.0222        | 2.1186 | 1000 | 0.1170          | 0.9754   | 0.9707   | 0.9674          | 0.9741       | 0.9710        |
+| 0.0139        | 2.5424 | 1200 | 0.2559          | 0.9594   | 0.9522   | 0.9434          | 0.9627       | 0.9710        |
+| 0.0165        | 2.9661 | 1400 | 0.1969          | 0.9679   | 0.9620   | 0.9559          | 0.9688       | 0.9710        |
+
+
+### Framework versions
+
+- Transformers 4.55.1
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\uacf5\uc815",
+    "1": "\ubd88\uacf5\uc815"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\uacf5\uc815": 0,
+    "\ubd88\uacf5\uc815": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86857b1c0072e03636b58b7c4cd8a8dbf6f98a879c25ef0f04e9de5ee400c07d
+size 442502744

runs/Aug17_07-26-56_246a9bc83487/events.out.tfevents.1755415617.246a9bc83487.1554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2f17e5cd482cc73fcdd18866d5a949ab1aaf4f823715ae6e3aebff5a04553e
+size 88

runs/Aug17_07-30-23_f08d0e0e5f8d/events.out.tfevents.1755415827.f08d0e0e5f8d.2286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ab727395b84221d1538fdfb9478a7b702651de9d72e1b0edd811adb117abcd
+size 5627

runs/Aug17_07-40-39_f08d0e0e5f8d/events.out.tfevents.1755416440.f08d0e0e5f8d.2286.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0dbecf1428952430495972f617e94aab598de2eb6bc079f2e60bfbd164c1cb
+size 6154

runs/Aug17_07-44-56_f08d0e0e5f8d/events.out.tfevents.1755416696.f08d0e0e5f8d.2286.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fef71a941bf0827aec51ee10d66f1a697e6bb2c37888380f443ce116c9898f5
+size 9646

runs/Aug17_07-53-54_f08d0e0e5f8d/events.out.tfevents.1755417235.f08d0e0e5f8d.2286.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dda6675c916931ad730496d86b842872f64b761b2b9ab97619be90e172053cf
+size 12342

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "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
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f9534718e4097947339da11e70d18f4e9f0409c8046f80eab7ad5b91bea040
+size 5368