Training complete - Task B

README.md

@@ -0,0 +1,17 @@
+---
+        language: code
+        license: mit
+        tags:
+        - code-classification
+        - ai-detection
+        ---
+
+        # GPAD2 Task B
+
+        Model trained for AI-generated code detection.
+
+        ## Training Details
+        - Epochs: 5
+        - Batch Size: 16
+        - Learning Rate: 2e-05
+        

checkpoint-220/config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "GPAD2Model"
+  ],
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-220/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad40f6d3d582df531f19ab778402bbf2aaf8b9e0649262e203cd8438965651c
+size 528375352

checkpoint-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa095c85fa3f2da927c0dad5aa6266759ad19437b9a20757d041b0a64dc1611b
+size 1056893771

checkpoint-220/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6bcccaa68ea0a809db7f44283fd3f02affd7ef090ffefc4f1f405a87f4d6058
+size 14645

checkpoint-220/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5319ab82eafef9abff26662764e32e7e2d4909e9d99554b9fcb53b120bd12b
+size 1383

checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc188b82b6c421a4e8dc18ce82d73cabe7a7863184ed02aab27e980cf25870d
+size 1465

checkpoint-220/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
+  }
+}

checkpoint-220/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>"
+}

checkpoint-220/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 4.354964733123779,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 1.3816,
+      "step": 100
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 16.470338821411133,
+      "learning_rate": 2.1212121212121216e-06,
+      "loss": 0.9388,
+      "step": 200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 998021268971520.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a0bee2c34548dafdd0503a630308960a9e799c5aeb869131fc5cb3b77ce3d6
+size 5841

config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "GPAD2Model"
+  ],
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

label_mapping.json

@@ -0,0 +1,43 @@
+{
+  "task": "B",
+  "num_labels": 11,
+  "label_names": [
+    "Human",
+    "DeepSeek-AI",
+    "Qwen",
+    "01-ai",
+    "BigCode",
+    "Gemma",
+    "Phi",
+    "Meta-LLaMA",
+    "IBM-Granite",
+    "Mistral",
+    "OpenAI"
+  ],
+  "label_to_id": {
+    "Human": 0,
+    "DeepSeek-AI": 1,
+    "Qwen": 2,
+    "01-ai": 3,
+    "BigCode": 4,
+    "Gemma": 5,
+    "Phi": 6,
+    "Meta-LLaMA": 7,
+    "IBM-Granite": 8,
+    "Mistral": 9,
+    "OpenAI": 10
+  },
+  "id_to_label": {
+    "0": "Human",
+    "1": "DeepSeek-AI",
+    "2": "Qwen",
+    "3": "01-ai",
+    "4": "BigCode",
+    "5": "Gemma",
+    "6": "Phi",
+    "7": "Meta-LLaMA",
+    "8": "IBM-Granite",
+    "9": "Mistral",
+    "10": "OpenAI"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad40f6d3d582df531f19ab778402bbf2aaf8b9e0649262e203cd8438965651c
+size 528375352

results.json

@@ -0,0 +1,64 @@
+{
+  "task": "B",
+  "train_result": {
+    "train_runtime": 63.5451,
+    "train_samples_per_second": 54.922,
+    "train_steps_per_second": 3.462,
+    "total_flos": 998021268971520.0,
+    "train_loss": 1.1348177476362749,
+    "epoch": 5.0
+  },
+  "eval_result": {
+    "eval_loss": 0.8116088509559631,
+    "eval_accuracy": 0.7535816618911175,
+    "eval_precision": 0.6650326670418545,
+    "eval_recall": 0.7535816618911175,
+    "eval_specificity": NaN,
+    "eval_f1": 0.6942659022778552,
+    "eval_auc": NaN,
+    "eval_pr_auc": NaN,
+    "eval_mcc": 0.4826800602055998,
+    "eval_balanced_accuracy": 0.20106890227872526,
+    "eval_runtime": 2.8095,
+    "eval_samples_per_second": 248.44,
+    "eval_steps_per_second": 7.83,
+    "epoch": 5.0
+  },
+  "config": {
+    "task": "B",
+    "base_model": "microsoft/codebert-base",
+    "num_labels": 11,
+    "stylometric_dim": 32,
+    "num_gpad_layers": 1,
+    "entropy_alpha": 0.1,
+    "max_length": 512,
+    "use_stylometric": true,
+    "num_epochs": 5,
+    "train_batch_size": 16,
+    "eval_batch_size": 32,
+    "learning_rate": 2e-05,
+    "weight_decay": 0.01,
+    "warmup_ratio": 0.1,
+    "max_grad_norm": 1.0,
+    "gradient_accumulation_steps": 1,
+    "use_mixed_precision": true,
+    "use_gradient_checkpointing": true,
+    "val_split": 0.2,
+    "sample_size": null,
+    "output_dir": "./gpad2_results_taskB_taskb",
+    "log_interval": 100,
+    "save_strategy": "steps",
+    "save_steps": 500,
+    "eval_strategy": "steps",
+    "eval_steps": 500,
+    "early_stopping_patience": 3,
+    "seed": 42,
+    "use_wandb": false,
+    "wandb_project": "gpad2_taskb",
+    "wandb_run_name": null,
+    "push_to_hub": true,
+    "hub_model_id": "ranjan56cse/gpad2-taskb_smpl",
+    "hub_token": null,
+    "hub_private_repo": false
+  }
+}

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 sha256:70a0bee2c34548dafdd0503a630308960a9e799c5aeb869131fc5cb3b77ce3d6
+size 5841