Upload CodeBERT SQL error classifier

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "JOIN_ERROR",
+    "1": "AGGREGATION_ERROR",
+    "2": "FILTER_ERROR",
+    "3": "WINDOW_FUNCTION_ERROR",
+    "4": "SUBQUERY_ERROR",
+    "5": "NULL_HANDLING_ERROR",
+    "6": "PERFORMANCE_ERROR",
+    "7": "LOGICAL_ERROR",
+    "8": "SYNTAX_ERROR"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AGGREGATION_ERROR": 1,
+    "FILTER_ERROR": 2,
+    "JOIN_ERROR": 0,
+    "LOGICAL_ERROR": 7,
+    "NULL_HANDLING_ERROR": 5,
+    "PERFORMANCE_ERROR": 6,
+    "SUBQUERY_ERROR": 4,
+    "SYNTAX_ERROR": 8,
+    "WINDOW_FUNCTION_ERROR": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

label_config.json

@@ -0,0 +1,18 @@
+{
+  "labels": [
+    "JOIN_ERROR",
+    "AGGREGATION_ERROR",
+    "FILTER_ERROR",
+    "WINDOW_FUNCTION_ERROR",
+    "SUBQUERY_ERROR",
+    "NULL_HANDLING_ERROR",
+    "PERFORMANCE_ERROR",
+    "LOGICAL_ERROR",
+    "SYNTAX_ERROR"
+  ],
+  "model_name": "microsoft/codebert-base",
+  "architecture": "codebert-cross-encoder",
+  "input_format": "QUESTION + SCHEMA + STUDENT_SQL + CORRECT_SQL",
+  "max_length": 512,
+  "threshold": 0.5
+}

metrics.json

@@ -0,0 +1,29 @@
+{
+  "train_samples": 12000,
+  "val_samples": 1500,
+  "test_samples": 1500,
+  "train_runtime": 1517.6384,
+  "validation": {
+    "eval_loss": 0.004817467648535967,
+    "eval_accuracy": 0.9926666666666667,
+    "eval_f1_macro": 0.9945474670443181,
+    "eval_f1_micro": 0.9933377748167888,
+    "eval_precision_macro": 0.9925154105309666,
+    "eval_recall_macro": 0.9966666666666667,
+    "eval_hamming_loss": 0.0014814814814814814,
+    "eval_subset_accuracy": 0.9926666666666667,
+    "eval_runtime": 21.7146,
+    "eval_samples_per_second": 69.078,
+    "eval_steps_per_second": 8.658,
+    "epoch": 2.0
+  },
+  "test": {
+    "accuracy": 0.9913333333333333,
+    "f1_macro": 0.9947790689667695,
+    "f1_micro": 0.9923409923409924,
+    "precision_macro": 0.9925405903330253,
+    "recall_macro": 0.9971111111111112,
+    "hamming_loss": 0.0017037037037037038,
+    "subset_accuracy": 0.9913333333333333
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f615885246c216a9423050b380ee25cedec1831d14b3eb9a64ace7d2c254b490
+size 498634356

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ecc99877e431f0fb553bc19b36eb32a69828581003a204660985bcd1a8b58b
+size 5841