Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: ealvaradob/bert-finetuned-phishing
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.00017717982700560242
+
+f1: 1.0
+
+precision: 1.0
+
+recall: 1.0
+
+auc: 1.0
+
+accuracy: 1.0

checkpoint-3/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "ealvaradob/bert-finetuned-phishing",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3183510f36fbb13dd0fd540496711d3b8375b4eee95dbf6d7b2efad67dc826f9
+size 1340622760

checkpoint-3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4434ae0c916a3f2ae27de1dbdcd43b532533329774cc3a63beba934d3a2a4f96
+size 2681469421

checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f513a4acbd095a23f5870520a930b5d7d8ff774bb32edd722cc35d675ce04c
+size 13990

checkpoint-3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9377a30cd58cb1ff51bbb1a408eede10e294d969bff51f8e1abed4cd85d4b318
+size 1064

checkpoint-3/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.00017717982700560242,
+  "best_model_checkpoint": "autotrain-e4ad1-545x6/checkpoint-3",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 101.7334213256836,
+      "learning_rate": 2e-05,
+      "loss": 4.0006,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_auc": 1.0,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 4.063055515289307,
+      "eval_precision": 0.5,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.5459,
+      "eval_samples_per_second": 1.294,
+      "eval_steps_per_second": 0.647,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 144.41079711914062,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 4.1033,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.000353464885847643,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.5395,
+      "eval_samples_per_second": 1.299,
+      "eval_steps_per_second": 0.65,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 52.38075637817383,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9852,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00017717982700560242,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.5336,
+      "eval_samples_per_second": 1.304,
+      "eval_steps_per_second": 0.652,
+      "step": 3
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 4,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "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": 4193691134976.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9604bdb326416447d73232df3140c6874332a9707b34591167f37f62e7e0a1a
+size 5176

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "ealvaradob/bert-finetuned-phishing",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3183510f36fbb13dd0fd540496711d3b8375b4eee95dbf6d7b2efad67dc826f9
+size 1340622760

runs/Jul09_09-02-56_r-prgarg007-safehouse-i132e2gj-0639f-li68t/events.out.tfevents.1720515778.r-prgarg007-safehouse-i132e2gj-0639f-li68t.317.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d161952c45aaf0e6cea283329bb593c06b0f46daefcf72246b416c481ea55f58
-size 5088
+oid sha256:c0f07291294767b068d37d262f42090e4c32ce27ecdb7db938ff468559f7e6cf
+size 8300

runs/Jul09_09-02-56_r-prgarg007-safehouse-i132e2gj-0639f-li68t/events.out.tfevents.1720515866.r-prgarg007-safehouse-i132e2gj-0639f-li68t.317.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f0ccef48db7826be65b01a87a4793d7fe2730486e6805df8b340d2ad11e070
+size 597

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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:b9604bdb326416447d73232df3140c6874332a9707b34591167f37f62e7e0a1a
+size 5176

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-e4ad1-545x6/autotrain-data",
+    "model": "ealvaradob/bert-finetuned-phishing",
+    "lr": 2e-05,
+    "epochs": 4,
+    "max_seq_length": 128,
+    "batch_size": 16,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.01,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "autotrain-e4ad1-545x6",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "prgarg007",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}