Upload 33 files

checkpoints/best_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab6b1e767a657af10be03aa9d120ec24513923b6db5344c978d5ed3e17bb164
+size 90868240

checkpoints/best_model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a105dc72136b80e271a5df6e94fbf47df50e727c1e2df31a89da53c2327a73f9
+size 180615546

checkpoints/best_model/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6995d36977a4d264aeee7abe1b8bf51f157c7c36958f49ab489019248b2531
+size 14244

checkpoints/best_model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d730b125295be3ba09f04773541436827552f0ed4b9a7d802caf45eb9b029cf
+size 1064

checkpoints/best_model/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

checkpoints/best_model/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_global_step": 330,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "D:\\ScamDetectProj\\DetectionMain\\checkpoints\\checkpoint-330",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00909090909090909,
+      "grad_norm": 0.9112464785575867,
+      "learning_rate": 0.0,
+      "loss": 0.693359375,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.12762108445167542,
+      "learning_rate": 2e-05,
+      "loss": 0.3843042566141951,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.995444,
+      "eval_f1": 0.995434,
+      "eval_loss": 0.012996933422982693,
+      "eval_precision": 0.995434,
+      "eval_recall": 0.995434,
+      "eval_runtime": 52.7986,
+      "eval_samples_per_second": 8.315,
+      "eval_steps_per_second": 0.265,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11700598150491714,
+      "learning_rate": 1.7780020181634713e-05,
+      "loss": 0.016534104130484843,
+      "step": 220
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.995444,
+      "eval_f1": 0.995413,
+      "eval_loss": 0.01899389922618866,
+      "eval_precision": 1.0,
+      "eval_recall": 0.990868,
+      "eval_runtime": 52.097,
+      "eval_samples_per_second": 8.427,
+      "eval_steps_per_second": 0.269,
+      "step": 220
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.05778728425502777,
+      "learning_rate": 1.5560040363269425e-05,
+      "loss": 0.005238141796805642,
+      "step": 330
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0006195309688337147,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 54.7945,
+      "eval_samples_per_second": 8.012,
+      "eval_steps_per_second": 0.256,
+      "step": 330
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3651f4bf0b82207e4e8abc076a222688334d0ae2bb1378384a54f8d6a6b27b93
+size 4792

checkpoints/best_model/training_config.json

@@ -0,0 +1,44 @@
+{
+  "PROJECT_ROOT": "D:\\ScamDetectProj\\DetectionMain",
+  "TEMP_DIR": "D:\\Temp\\scam_detection",
+  "TRANSCRIPT_DIR": "D:\\ScamDetectProj\\DetectionMain\\Transcript",
+  "LEGITIMATE_DIR": "D:\\ScamDetectProj\\DetectionMain\\Transcript\\legitimate",
+  "SCAM_DIR": "D:\\ScamDetectProj\\DetectionMain\\Transcript\\scam",
+  "CHECKPOINT_DIR": "D:\\ScamDetectProj\\DetectionMain\\checkpoints",
+  "BEST_MODEL_DIR": "D:\\ScamDetectProj\\DetectionMain\\checkpoints\\best_model",
+  "OUTPUTS_DIR": "D:\\ScamDetectProj\\DetectionMain\\outputs",
+  "TRAIN_CSV": "D:\\ScamDetectProj\\DetectionMain\\train.csv",
+  "VAL_CSV": "D:\\ScamDetectProj\\DetectionMain\\val.csv",
+  "TEST_CSV": "D:\\ScamDetectProj\\DetectionMain\\test.csv",
+  "TRAIN_SPLIT": 0.8,
+  "VAL_SPLIT": 0.1,
+  "TEST_SPLIT": 0.1,
+  "RANDOM_SEED": 42,
+  "MODEL_NAME": "sentence-transformers/all-MiniLM-L6-v2",
+  "EMBEDDING_DIM": 384,
+  "NUM_LABELS": 2,
+  "DROPOUT_RATE": 0.2,
+  "MAX_LENGTH": 256,
+  "LABEL_MAP": {
+    "legitimate": 0,
+    "scam": 1
+  },
+  "ID2LABEL": {
+    "0": "LEGITIMATE",
+    "1": "SCAM"
+  },
+  "LEARNING_RATE": 2e-05,
+  "WEIGHT_DECAY": 0.01,
+  "WARMUP_RATIO": 0.1,
+  "NUM_EPOCHS": 10,
+  "BATCH_SIZE": 16,
+  "GRADIENT_ACCUMULATION_STEPS": 1,
+  "MAX_GRAD_NORM": 1.0,
+  "EARLY_STOPPING_PATIENCE": 3,
+  "EARLY_STOPPING_METRIC": "f1",
+  "USE_MIXED_PRECISION": true,
+  "ONNX_PATH": "D:\\ScamDetectProj\\DetectionMain\\outputs\\scam_detector.onnx",
+  "TORCHSCRIPT_PATH": "D:\\ScamDetectProj\\DetectionMain\\outputs\\scam_detector.pt",
+  "HF_API_KEY": "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",
+  "max_length": 512
+}

checkpoints/checkpoint-113/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5a874e604975ab5de3fd42e14cb42d4f2da6a606931b0728c6c490c376742f
+size 90868240

checkpoints/checkpoint-113/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd680e08ddf38d1fc8936b99413a8589e27f34f144aa08eb79a4ddc4efe78ac
+size 180615546

checkpoints/checkpoint-113/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6205695d30395aae4a5b7aa561457d8ceaab07e8110d161c2b8b68f4493e5ab2
+size 14244

checkpoints/checkpoint-113/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d520a4a3f67fa2db0aae3e86831c61fad772ed2f7fffa2e53b70ea6fb81a3ff1
+size 1064

checkpoints/checkpoint-113/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

checkpoints/checkpoint-113/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": 113,
+  "best_metric": 0.975281,
+  "best_model_checkpoint": "D:\\ScamDetectProj\\DetectionMain\\checkpoints\\checkpoint-113",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008849557522123894,
+      "grad_norm": 0.731779158115387,
+      "learning_rate": 0.0,
+      "loss": 0.6741943359375,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.90731430053711,
+      "learning_rate": 2e-05,
+      "loss": 0.4483108179909842,
+      "step": 113
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.97561,
+      "eval_f1": 0.975281,
+      "eval_loss": 0.061309635639190674,
+      "eval_precision": 0.986364,
+      "eval_recall": 0.964444,
+      "eval_runtime": 149.177,
+      "eval_samples_per_second": 3.023,
+      "eval_steps_per_second": 0.101,
+      "step": 113
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-113/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414e9587835d93510efd94098e1539f6eec7332fe08702764d45e17fe065b18f
+size 4792

checkpoints/checkpoint-226/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c6c4a55064614b7a20523165f18cf3d540eeebf8060334520ac3e9c9f46bb5
+size 90868240

checkpoints/checkpoint-226/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aac2970165630973165345e8565b4c643c2eed409a172236abb8d5de8d6474e
+size 180615546

checkpoints/checkpoint-226/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6186aec27672b4a0eeaae78a7f8401dc9fa34d96a28a17aab7b8e11f0822a1af
+size 14244

checkpoints/checkpoint-226/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b2d214c8bf6c28c32a03de6706121cd982c31bbe362b3ba44663eb1be8c5f1
+size 1064

checkpoints/checkpoint-226/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

checkpoints/checkpoint-226/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_global_step": 226,
+  "best_metric": 0.997773,
+  "best_model_checkpoint": "D:\\ScamDetectProj\\DetectionMain\\checkpoints\\checkpoint-226",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 226,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008849557522123894,
+      "grad_norm": 0.731779158115387,
+      "learning_rate": 0.0,
+      "loss": 0.6741943359375,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.90731430053711,
+      "learning_rate": 2e-05,
+      "loss": 0.4483108179909842,
+      "step": 113
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.97561,
+      "eval_f1": 0.975281,
+      "eval_loss": 0.061309635639190674,
+      "eval_precision": 0.986364,
+      "eval_recall": 0.964444,
+      "eval_runtime": 149.177,
+      "eval_samples_per_second": 3.023,
+      "eval_steps_per_second": 0.101,
+      "step": 113
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.09732598066329956,
+      "learning_rate": 1.7779960707269156e-05,
+      "loss": 0.03951404368982906,
+      "step": 226
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.997783,
+      "eval_f1": 0.997773,
+      "eval_loss": 0.005174789112061262,
+      "eval_precision": 1.0,
+      "eval_recall": 0.995556,
+      "eval_runtime": 117.348,
+      "eval_samples_per_second": 3.843,
+      "eval_steps_per_second": 0.128,
+      "step": 226
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-226/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414e9587835d93510efd94098e1539f6eec7332fe08702764d45e17fe065b18f
+size 4792

checkpoints/checkpoint-339/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a0f9f7f29d8e827b2030a9415a435801ae977cdb84dd93b0421653df25484f
+size 90868240

checkpoints/checkpoint-339/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7af6e274a31ff4040282ea48a8c2aaa7c0cce0224558950196f506c7b40a7d
+size 180615546

checkpoints/checkpoint-339/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e42ff2e0d5a5f2cd6fd813defab97c3625457527e2a6a7f20b73989d7f144f2
+size 14244

checkpoints/checkpoint-339/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0704fff9343faf544fb5ff651cc21a4d6658e6926af54f114844b926d2587fc2
+size 1064

checkpoints/checkpoint-339/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

checkpoints/checkpoint-339/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_global_step": 339,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "D:\\ScamDetectProj\\DetectionMain\\checkpoints\\checkpoint-339",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 339,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008849557522123894,
+      "grad_norm": 0.731779158115387,
+      "learning_rate": 0.0,
+      "loss": 0.6741943359375,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.90731430053711,
+      "learning_rate": 2e-05,
+      "loss": 0.4483108179909842,
+      "step": 113
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.97561,
+      "eval_f1": 0.975281,
+      "eval_loss": 0.061309635639190674,
+      "eval_precision": 0.986364,
+      "eval_recall": 0.964444,
+      "eval_runtime": 149.177,
+      "eval_samples_per_second": 3.023,
+      "eval_steps_per_second": 0.101,
+      "step": 113
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.09732598066329956,
+      "learning_rate": 1.7779960707269156e-05,
+      "loss": 0.03951404368982906,
+      "step": 226
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.997783,
+      "eval_f1": 0.997773,
+      "eval_loss": 0.005174789112061262,
+      "eval_precision": 1.0,
+      "eval_recall": 0.995556,
+      "eval_runtime": 117.348,
+      "eval_samples_per_second": 3.843,
+      "eval_steps_per_second": 0.128,
+      "step": 226
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.07887029647827148,
+      "learning_rate": 1.555992141453831e-05,
+      "loss": 0.00823842424207029,
+      "step": 339
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00027296337066218257,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 121.5059,
+      "eval_samples_per_second": 3.712,
+      "eval_steps_per_second": 0.123,
+      "step": 339
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-339/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414e9587835d93510efd94098e1539f6eec7332fe08702764d45e17fe065b18f
+size 4792