End of training

README.md

@@ -1,7 +1,6 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: microsoft/codebert-base
 tags:
 - generated_from_trainer
 metrics:
@@ -17,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-practice-classifier
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5419
-- Accuracy: 0.524
-- Auc: 0.65
-- Precision: 0.714
+- Loss: 0.1945
+- Accuracy: 0.981
+- Auc: 0.998
+- Precision: 0.944
 
 ## Model description
 
@@ -42,8 +41,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 5
-- eval_batch_size: 5
+- train_batch_size: 8
+- eval_batch_size: 8
 - 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
@@ -53,21 +52,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc   | Precision |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|:---------:|
-| 0.5815        | 1.0   | 34   | 0.6348          | 0.619    | 0.688 | 0.9       |
-| 0.5744        | 2.0   | 68   | 0.5624          | 0.667    | 0.688 | 0.765     |
-| 0.5532        | 3.0   | 102  | 0.5057          | 0.762    | 0.688 | 0.789     |
-| 0.563         | 4.0   | 136  | 0.5677          | 0.571    | 0.688 | 0.769     |
-| 0.514         | 5.0   | 170  | 0.5423          | 0.667    | 0.662 | 0.765     |
-| 0.5349        | 6.0   | 204  | 0.5564          | 0.571    | 0.65  | 0.769     |
-| 0.5298        | 7.0   | 238  | 0.5672          | 0.571    | 0.65  | 0.769     |
-| 0.4964        | 8.0   | 272  | 0.5173          | 0.667    | 0.65  | 0.765     |
-| 0.5083        | 9.0   | 306  | 0.5435          | 0.571    | 0.65  | 0.769     |
-| 0.4908        | 10.0  | 340  | 0.5419          | 0.524    | 0.65  | 0.714     |
+| 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     |
 
 
 ### Framework versions
 
-- Transformers 4.48.3
-- Pytorch 2.5.1+cu124
-- Datasets 3.3.2
-- Tokenizers 0.21.0
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -1,33 +1,36 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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,
   "id2label": {
-    "0": "Bad Practice",
-    "1": "Good Practice"
+    "0": "pas vulnerable",
+    "1": "vulnerable"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
-    "Bad Practice": 0,
-    "Good Practice": 1
+    "pas vulnerable": 0,
+    "vulnerable": 1
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "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",
   "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": "4.48.3",
-  "vocab_size": 30522
+  "transformers_version": "4.50.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8077e7bc94d39ae7cc98e34e9c0a0be850100d69f0755dafa7dc6abf3fccde4c
-size 267832560
+oid sha256:f4e37cbb8cc4169c511a9d3da2cd51f1487c31f949995b650a8ae776ebe45697
+size 498612824

runs/Mar30_04-11-20_fe78b26bd799/events.out.tfevents.1743307898.fe78b26bd799.602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1d9565607f0bb03296fc6e72cb737fe5a33c3dbc57dcd20c8fb765bbddf056
+size 11891

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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
+  }
 }

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11019076554685cecf69d2137a562e0858fea104819f5ebdb8244a1776f96cc0
+oid sha256:eba35b10637c3e19cd59d78e2fb39be7749ec5066f178e19b8e9c4f9249c43d2
 size 5368