majorSeaweed/distilled_Bert_Uncased_FishingURL_Student_Finetuned

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google-bert/bert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -16,11 +16,11 @@ 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.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3163
-- Accuracy: 0.88
-- Auc: 0.942
+- Loss: 0.3179
+- Accuracy: 0.878
+- Auc: 0.938
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc   |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|
-| 0.5461        | 1.0   | 66   | 0.4358          | 0.813    | 0.907 |
-| 0.4341        | 2.0   | 132  | 0.3788          | 0.849    | 0.929 |
-| 0.3861        | 3.0   | 198  | 0.3485          | 0.871    | 0.937 |
-| 0.3734        | 4.0   | 264  | 0.3526          | 0.86     | 0.937 |
-| 0.364         | 5.0   | 330  | 0.3266          | 0.88     | 0.94  |
-| 0.3323        | 6.0   | 396  | 0.3308          | 0.876    | 0.942 |
-| 0.3358        | 7.0   | 462  | 0.3447          | 0.862    | 0.942 |
-| 0.3292        | 8.0   | 528  | 0.3147          | 0.882    | 0.942 |
-| 0.3361        | 9.0   | 594  | 0.3148          | 0.878    | 0.942 |
-| 0.3212        | 10.0  | 660  | 0.3163          | 0.88     | 0.942 |
+| 0.3942        | 1.0   | 66   | 0.3788          | 0.844    | 0.915 |
+| 0.359         | 2.0   | 132  | 0.3501          | 0.86     | 0.926 |
+| 0.3338        | 3.0   | 198  | 0.3484          | 0.862    | 0.932 |
+| 0.3183        | 4.0   | 264  | 0.3376          | 0.871    | 0.934 |
+| 0.298         | 5.0   | 330  | 0.3252          | 0.88     | 0.936 |
+| 0.298         | 6.0   | 396  | 0.3215          | 0.876    | 0.937 |
+| 0.297         | 7.0   | 462  | 0.3234          | 0.876    | 0.937 |
+| 0.2918        | 8.0   | 528  | 0.3188          | 0.882    | 0.938 |
+| 0.2862        | 9.0   | 594  | 0.3194          | 0.871    | 0.938 |
+| 0.2823        | 10.0  | 660  | 0.3179          | 0.878    | 0.938 |
 
 
 ### Framework versions

config.json

@@ -1,35 +1,33 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "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,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "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": "4.49.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe60468fef58862b3dd8731eca71033fa658bc1d36b23440219856369866360
-size 437958648
+oid sha256:74ca6daba73b3e77f2848af6a8b11f7d8a460ad38d98fd5343d446f2e65a08ea
+size 267832560

runs/Mar19_08-35-02_2097af05189c/events.out.tfevents.1742373344.2097af05189c.2406.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb280866c12b3d0dbe5053c05090ccf238f836b04744e86a290970614308fac
+size 5126

runs/Mar19_08-35-02_2097af05189c/events.out.tfevents.1742373391.2097af05189c.2406.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b144ba073e4801cfd3fb26d20109f1ac2088258242b4cae6c5a78d50c55fd0
+size 11328

tokenizer.json

@@ -6,7 +6,16 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:251dfc39cd6d805d7ae07a3cfdc61360630ff023ccb1645784ee78e9644278b2
+oid sha256:3237c670a651633477c6bc9322909a75df125d0008804fbab1b0885a0e8ae14f
 size 5368