djsull/aha_class_v1

README.md

@@ -0,0 +1,71 @@
+---
+base_model: klue/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: aha_class_v1
+  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. -->
+
+# aha_class_v1
+
+This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0923
+- F1: 0.9620
+- Roc Auc: 0.9701
+- Accuracy: 0.9391
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| No log        | 1.0   | 42   | 0.1469          | 0.9620 | 0.9701  | 0.9304   |
+| No log        | 2.0   | 84   | 0.1095          | 0.9661 | 0.9724  | 0.9478   |
+| No log        | 3.0   | 126  | 0.1102          | 0.9447 | 0.9553  | 0.9217   |
+| No log        | 4.0   | 168  | 0.1090          | 0.9536 | 0.9637  | 0.9304   |
+| No log        | 5.0   | 210  | 0.0923          | 0.9620 | 0.9701  | 0.9391   |
+| No log        | 6.0   | 252  | 0.1059          | 0.9461 | 0.9613  | 0.9130   |
+| No log        | 7.0   | 294  | 0.1125          | 0.9620 | 0.9701  | 0.9478   |
+| No log        | 8.0   | 336  | 0.0942          | 0.9664 | 0.9743  | 0.9478   |
+| No log        | 9.0   | 378  | 0.0958          | 0.9667 | 0.9763  | 0.9478   |
+| No log        | 10.0  | 420  | 0.0956          | 0.9705 | 0.9766  | 0.9565   |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "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": "Normal",
+    "1": "Service",
+    "2": "Token"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Normal": 0,
+    "Service": 1,
+    "Token": 2
+  },
+  "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": "multi_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "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:f8d366400660ce725767b78b62d02cb3434723de89c8e3d2e3c0e22bba3c82e8
+size 442505820

runs/Sep27_03-20-20_129-146-79-76/events.out.tfevents.1727407221.129-146-79-76.1422139.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577c16ac3a3590b353efb230e0bcd1372f95754298e6a2a4d4f4963ee8c2d290
+size 9638

runs/Sep27_03-20-20_129-146-79-76/events.out.tfevents.1727407577.129-146-79-76.1422139.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a126fec641d1391c00a9cfa15002cc370750a60ae5da872185107daf7f5ca1
+size 508

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 +1,59 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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 sha256:5f63eaa98a66c5a0e0680ec903bdac6e54739f4b040215f4fbc9266a8b4e3487
+size 5112