bert-finetuned-classification-hatespeech

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-fintuned-classification
+  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-fintuned-classification
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8246
+- Accuracy: 0.6533
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.7446        | 1.0   | 4030  | 0.8818          | 0.6436   |
+| 0.6034        | 2.0   | 8060  | 1.2037          | 0.6589   |
+| 0.4216        | 3.0   | 12090 | 1.8246          | 0.6533   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.2.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "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": "normal",
+    "1": "offensive",
+    "2": "hatespeech"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "hatespeech": 2,
+    "normal": 0,
+    "offensive": 1
+  },
+  "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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e941f063b794cbac43701a82364a4e52776c303d303450362733998023d89561
+size 433273844

runs/Jul16_10-34-22_ip-10-192-12-104/events.out.tfevents.1721126115.ip-10-192-12-104.2815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42dc04c17cff6e6134a7da10dcb6e4f8078b0a7c26587cf0712ec8ea83b39f5
+size 4928

runs/Jul16_10-41-11_ip-10-192-12-104/events.out.tfevents.1721126472.ip-10-192-12-104.2815.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bed8624a1e541affe12779c33b579fa768a2b761baf03882124273618c55a2
+size 5027

runs/Jul16_10-43-51_ip-10-192-12-104/events.out.tfevents.1721126633.ip-10-192-12-104.2815.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc041249185ee6d0e5073c847875de5779b19cc6d766b632911c232bbb5166e
+size 5027

runs/Jul16_10-45-39_ip-10-192-12-104/events.out.tfevents.1721126761.ip-10-192-12-104.2815.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0accc74f5ba12e441cda5993f007b938ceb02c747233033cbbeea9a81242cbc
+size 5027

runs/Jul16_10-45-39_ip-10-192-12-104/events.out.tfevents.1721126793.ip-10-192-12-104.2815.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa27a74e24b52be4ad1103e293b05c5add6ba4580baf20b8cfb1fb3dbfe60d0e
+size 5076

runs/Jul16_10-45-39_ip-10-192-12-104/events.out.tfevents.1721126856.ip-10-192-12-104.2815.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df46cce004c104ea9ed784ee8b8cd8b2bc024ea1b2330834936d86e9eee61de
+size 5076

runs/Jul16_10-45-39_ip-10-192-12-104/events.out.tfevents.1721126869.ip-10-192-12-104.2815.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2652e3ea854314b5c6573a0732aa9eb6a5e89bcca7c89735a3fba337cae6df
+size 5076

runs/Jul16_10-45-39_ip-10-192-12-104/events.out.tfevents.1721126882.ip-10-192-12-104.2815.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db11287447e7c253a6fc5dcaaf69b73720a5a6d0b819a5335071749eb4928b51
+size 5076

runs/Jul16_10-45-39_ip-10-192-12-104/events.out.tfevents.1721126913.ip-10-192-12-104.2815.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c9867e6bd63a2c5c2e6bb5c83f79a938b935e54c01cef56d8654cfde4efc5c
+size 5076

runs/Jul16_10-45-39_ip-10-192-12-104/events.out.tfevents.1721127076.ip-10-192-12-104.2815.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17603136fefb1d1a6f15187e51b57b7c7c1d5afd4942ec52bf1590fbe3e2c277
+size 5076

runs/Jul16_11-01-21_ip-10-192-12-104/events.out.tfevents.1721127698.ip-10-192-12-104.2815.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54244da79e2d25e1680a517f8427a7a8d298a1d414aca9ee2bc9803a0411e120
+size 5027

runs/Jul16_11-03-07_ip-10-192-12-104/events.out.tfevents.1721127789.ip-10-192-12-104.2815.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ab37d67529e835d82bd7422c74b0a7f64a60a454f99d360779e770f7e558a12
+size 7616

runs/Jul16_18-51-37_ip-10-192-12-10/events.out.tfevents.1721155902.ip-10-192-12-10.1725.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082d27cab73c8ed45a85623e161cb3bf7da325507375119c0d59dace4a5df186
+size 11411

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 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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 sha256:4e29423ad850f53a47242d903223e8c6b44c4ca015b0d32f1e9203ba1e4506e5
+size 5176