majorSeaweed/Bert_Uncased_FishingURL_Teacher

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-phishing-classifier_teacher
+  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. -->
+
+# bert-phishing-classifier_teacher
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3024
+- Accuracy: 0.878
+- Auc: 0.949
+
+## 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: 0.0002
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc   |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|
+| 0.4639        | 1.0   | 66   | 0.4104          | 0.802    | 0.905 |
+| 0.4068        | 2.0   | 132  | 0.3689          | 0.82     | 0.924 |
+| 0.3667        | 3.0   | 198  | 0.3378          | 0.858    | 0.937 |
+| 0.3631        | 4.0   | 264  | 0.3409          | 0.853    | 0.939 |
+| 0.3543        | 5.0   | 330  | 0.3168          | 0.873    | 0.945 |
+| 0.3234        | 6.0   | 396  | 0.3221          | 0.862    | 0.947 |
+| 0.328         | 7.0   | 462  | 0.3362          | 0.851    | 0.948 |
+| 0.3251        | 8.0   | 528  | 0.3012          | 0.876    | 0.949 |
+| 0.3316        | 9.0   | 594  | 0.3011          | 0.88     | 0.949 |
+| 0.3193        | 10.0  | 660  | 0.3024          | 0.878    | 0.949 |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Safe",
+    "1": "Not Safe"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Not Safe": 1,
+    "Safe": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "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 sha256:9e6ab1ae5b038dada7b5298c17fe7dc40f39afad84db0cec31bf6497900ae3f8
+size 437958648

runs/Mar14_17-51-58_66f7b63fce3b/events.out.tfevents.1741974754.66f7b63fce3b.312.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341e03d016d09bef4328dcf15e2ccfb180e7f226b3cbc4387ae97d256e2a5e83
+size 11384

runs/Mar14_17-56-22_66f7b63fce3b/events.out.tfevents.1741974985.66f7b63fce3b.312.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17c5319806b65b466e6aa4fb86914b8d8d7eadb39e54312e209a20a7e493634
+size 5842

runs/Mar14_17-57-14_66f7b63fce3b/events.out.tfevents.1741975038.66f7b63fce3b.312.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fa41f5a4b1f5a63465a1593d98ce635534b051ffa722f554bd544d97cef883
+size 9488

runs/Mar14_18-00-01_66f7b63fce3b/events.out.tfevents.1741975204.66f7b63fce3b.312.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec52c543d32ef7cd4217a601bb3d41390bf8fb50c396a14e60c8b40eb90fc63
+size 5222

runs/Mar14_18-00-17_66f7b63fce3b/events.out.tfevents.1741975218.66f7b63fce3b.312.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4dba17b9243d64166ebcb9691121ba9bca6936fa524409f4b9bed18b9f3b46e
+size 11424

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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 sha256:07a452f6b3a66e25461ce72e0ede5c1b8b0f6e4d8315253c64339814492dc4f6
+size 5368