initial commit

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- text-classification
+- generated_from_trainer
+model-index:
+- name: harssment_classifier
+  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. -->
+
+# harssment_classifier
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2221
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.2471        | 1.0   | 2435  | 0.2247          |
+| 0.1698        | 2.0   | 4870  | 0.2438          |
+| 0.1131        | 3.0   | 7305  | 0.3530          |
+| 0.0587        | 4.0   | 9740  | 0.4432          |
+| 0.0187        | 5.0   | 12175 | 0.5102          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "non-harassment",
+    "1": "harassment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "harassment": 1,
+    "non-harassment": 0
+  },
+  "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": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab676484e2222a550fa8a944843baf7aa41b86de0ae76ecbe464f0a03fcbed22
+size 437958648

runs/May15_20-00-33_40cb094255b7/events.out.tfevents.1715803269.40cb094255b7.3808.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06df2304396e84c9b36132f51e7cf8ea5d746d60a400e298078f9f994ee3fce3
+size 4184

runs/May15_20-01-51_40cb094255b7/events.out.tfevents.1715803317.40cb094255b7.3808.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c1d17b332f1a30cbbe49d2cf4e65be5a4e5bd151a7fb9b8e2641b0374eedf4
+size 4184

runs/May15_20-04-16_40cb094255b7/events.out.tfevents.1715803458.40cb094255b7.5892.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e46f183598bb4fc01a7d31e00da4563dada09fa3b5c732e34f35dffe1aa0fb
+size 4808

runs/May15_20-07-03_40cb094255b7/events.out.tfevents.1715803627.40cb094255b7.5892.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079ae47df9468f6ca002217e41ffd21983520a63001f46f3052a41165262f984
+size 4808

runs/May15_20-10-42_40cb094255b7/events.out.tfevents.1715803847.40cb094255b7.5892.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dacb65cfd945c5917cae46e4f505e9911b9b680315f75fdd6abebdb2939d8799
+size 5019

runs/May15_20-15-13_40cb094255b7/events.out.tfevents.1715804121.40cb094255b7.5892.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2a94d7752df0a547a8be183012e98abec5dddf88a3ac772c974d7aff685fea
+size 4859

runs/May15_20-15-42_40cb094255b7/events.out.tfevents.1715804144.40cb094255b7.5892.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc1f16e5b9972e6af952d3ec2c79e004890c6aaad7a02f6266fd36c09c19186
+size 11632

runs/May15_20-15-42_40cb094255b7/events.out.tfevents.1715811801.40cb094255b7.5892.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14cccc2860f3544c2738c563335372244eee4179dc624acab511a744a413402d
+size 359

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": true,
+  "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 sha256:37ca557c52ce58ee11426fbcbbd58ae563a5650e3658ebbb6aa66c7052c5399f
+size 4984