End of training

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-base_model: microsoft/codebert-base
+license: apache-2.0
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -16,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-practice-classifier
 
-This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on the None dataset.
+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: 0.1945
-- Accuracy: 0.981
-- Auc: 0.998
-- Precision: 0.944
+- Loss: 0.7264
+- Accuracy: 0.375
+- Auc: 0.133
+- Precision: 0.333
 
 ## Model description
 
@@ -52,16 +53,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc   | Precision |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|:---------:|
-| 0.6508        | 1.0   | 26   | 0.4846          | 0.83     | 0.966 | 1.0       |
-| 0.5433        | 2.0   | 52   | 0.4160          | 0.717    | 0.975 | 1.0       |
-| 0.5118        | 3.0   | 78   | 0.3608          | 0.925    | 0.993 | 0.81      |
-| 0.4396        | 4.0   | 104  | 0.3048          | 0.981    | 0.997 | 1.0       |
-| 0.3796        | 5.0   | 130  | 0.2879          | 0.906    | 0.998 | 1.0       |
-| 0.3277        | 6.0   | 156  | 0.2418          | 0.962    | 0.998 | 0.895     |
-| 0.3202        | 7.0   | 182  | 0.2406          | 0.962    | 0.998 | 1.0       |
-| 0.278         | 8.0   | 208  | 0.2087          | 0.962    | 0.998 | 0.895     |
-| 0.2823        | 9.0   | 234  | 0.1968          | 0.962    | 0.998 | 0.941     |
-| 0.2718        | 10.0  | 260  | 0.1945          | 0.981    | 0.998 | 0.944     |
+| 0.6963        | 1.0   | 4    | 0.7382          | 0.375    | 0.133 | 0.375     |
+| 0.6877        | 2.0   | 8    | 0.7270          | 0.375    | 0.133 | 0.375     |
+| 0.6984        | 3.0   | 12   | 0.7126          | 0.25     | 0.067 | 0.2       |
+| 0.6871        | 4.0   | 16   | 0.7091          | 0.375    | 0.133 | 0.0       |
+| 0.6912        | 5.0   | 20   | 0.7012          | 0.5      | 0.133 | 0.0       |
+| 0.6867        | 6.0   | 24   | 0.7062          | 0.5      | 0.133 | 0.0       |
+| 0.6862        | 7.0   | 28   | 0.7095          | 0.375    | 0.133 | 0.0       |
+| 0.6639        | 8.0   | 32   | 0.7177          | 0.25     | 0.133 | 0.0       |
+| 0.67          | 9.0   | 36   | 0.7239          | 0.125    | 0.133 | 0.0       |
+| 0.6597        | 10.0  | 40   | 0.7264          | 0.375    | 0.133 | 0.333     |
 
 
 ### Framework versions

config.json

@@ -1,36 +1,32 @@
 {
+  "activation": "gelu",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "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": "pas vulnerable",
-    "1": "vulnerable"
+    "0": "Bad Practice",
+    "1": "Good Practice"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
-    "pas vulnerable": 0,
-    "vulnerable": 1
+    "Bad Practice": 0,
+    "Good Practice": 1
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "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": "4.50.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e37cbb8cc4169c511a9d3da2cd51f1487c31f949995b650a8ae776ebe45697
-size 498612824
+oid sha256:6c24afbd14d800508ffeba0e879058592bc80be0249c49f78f7029ba5efb14ed
+size 267832560

runs/Mar30_04-34-29_4e6c655b6721/events.out.tfevents.1743309763.4e6c655b6721.1007.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55be930a2a87502f11790425a5166dadbcf934267b4806a0f73b7f94ba661925
+size 11667

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,58 +1,56 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
   "extra_special_tokens": {},
-  "mask_token": "<mask>",
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba35b10637c3e19cd59d78e2fb39be7749ec5066f178e19b8e9c4f9249c43d2
+oid sha256:27153ef153cd5fb9313dccf6dba6eb925400e20bef3bcd5f04e12b0d5d594a58
 size 5368