End of training

README.md

@@ -1,10 +1,62 @@
-Example use:
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-large-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: cyberbullying_classifier
+  results: []
+---
 
-from transformers import pipeline
-text = "This was a masterpiece. Not completely faithful to the books, but enthralling from beginning to end. Might be my favorite of the three."
+<!-- 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. -->
 
+# cyberbullying_classifier
 
-classifier = pipeline("sentiment-analysis", model="ekurtulus/cyberbullying_classifier")
-classifier(text)
+This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4109
+- Accuracy: 0.8762
 
-# label=0 not bullying, label=1 bullying
+## 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: 16
+- eval_batch_size: 16
+- 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: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2371        | 1.0   | 895  | 0.3629          | 0.8584   |
+| 0.1252        | 2.0   | 1790 | 0.4109          | 0.8762   |
+
+
+### Framework versions
+
+- Transformers 4.52.3
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.1

config.json

@@ -1,24 +1,39 @@
 {
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.52.2",
-  "vocab_size": 30522
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f9cb16d3268ebc49d7e2ae292a798e4bca625454058c51b61d5f57b257f92d
-size 267832560
+oid sha256:ca96d9e677a973119b51c1de79152432f7ce32d76f4cbe5d3ef12c87b19a5088
+size 1334372264

runs/Jun05_22-47-36_012f435e25f8/events.out.tfevents.1749163660.012f435e25f8.911.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f48d10afcba7f0b958fa6117c6394ab5b3d2f7519aee3ac0b52db2f43f3b889
+size 5210

runs/Jun05_22-48-02_012f435e25f8/events.out.tfevents.1749163682.012f435e25f8.911.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0cec35969e405c0166a2ce977ddd6fef095ef0551cd67eda3346781e6096aa
+size 5210

runs/Jun05_22-49-40_012f435e25f8/events.out.tfevents.1749163781.012f435e25f8.911.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf48162c3c326af977896c6b2f7ec42fe8d32150df51b338271d01c7458f3823
+size 131796

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c15f4bf0aa5e41335bde28fde366d1ddfab76be4f0b4c9d0c0b0a5b8035a236
+oid sha256:85444d279c6324abf6b67c58db44162ad018132d2f23690dcd610184cd1977fc
 size 5304