malecada-phishing-email-classifier

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6801
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5048        | 1.0   | 208  | 0.4436          |
+| 0.3539        | 2.0   | 416  | 0.5064          |
+| 0.2982        | 3.0   | 624  | 0.4879          |
+| 0.2457        | 4.0   | 832  | 0.4303          |
+| 0.1879        | 5.0   | 1040 | 0.5073          |
+| 0.1542        | 6.0   | 1248 | 0.5062          |
+| 0.1273        | 7.0   | 1456 | 0.6459          |
+| 0.1017        | 8.0   | 1664 | 0.7306          |
+| 0.0919        | 9.0   | 1872 | 0.6311          |
+| 0.0821        | 10.0  | 2080 | 0.6049          |
+| 0.0752        | 11.0  | 2288 | 0.8128          |
+| 0.0629        | 12.0  | 2496 | 0.6608          |
+| 0.0609        | 13.0  | 2704 | 0.7059          |
+| 0.0555        | 14.0  | 2912 | 0.6801          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "legit",
+    "1": "spam",
+    "2": "malicious"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "legit": 0,
+    "malicious": 2,
+    "spam": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b418a39084a44aebc7ecc82a05b3a82f8813fdf041a7a5cd9cd4013802bb139b
+size 267835644

runs/Aug07_10-16-54_ea715cf5a7ab/events.out.tfevents.1723025815.ea715cf5a7ab.1877.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376a37ea2316d544d85477a479cf377bd2450ab88f7f908cbc430979ac795123
+size 8224

runs/Aug07_10-53-52_ea715cf5a7ab/events.out.tfevents.1723028033.ea715cf5a7ab.1877.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae7365700b68cdc1e401bbf0da5e54cb397ae356d59988bc88d0e5829e17be7
+size 88

runs/Aug07_10-54-28_ea715cf5a7ab/events.out.tfevents.1723028069.ea715cf5a7ab.12155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e794853553e75731cd132d937f3e23462209b532f10687adea1f18a537f1861
+size 12080

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bf7050750cf65510ccabeac6402adfddca4cd7dfeb94d5c901977b41494609
+size 5176