End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: brand-safety-model
+  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. -->
+
+# brand-safety-model
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3497
+- Accuracy: 0.6355
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.319         | 1.0   | 65   | 2.7462          | 0.4230   |
+| 2.6272        | 2.0   | 130  | 2.0795          | 0.5010   |
+| 2.137         | 3.0   | 195  | 1.6683          | 0.5770   |
+| 1.469         | 4.0   | 260  | 1.4721          | 0.6101   |
+| 1.2405        | 5.0   | 325  | 1.3497          | 0.6355   |
+| 1.1023        | 6.0   | 390  | 1.2936          | 0.6335   |
+| 0.9206        | 7.0   | 455  | 1.2855          | 0.6316   |
+| 0.8374        | 8.0   | 520  | 1.2579          | 0.6355   |
+| 0.794         | 9.0   | 585  | 1.2525          | 0.6335   |
+| 0.7388        | 10.0  | 650  | 1.2478          | 0.6316   |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,101 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Pornography",
+    "1": "Erotica",
+    "2": "Adult Content",
+    "3": "Crime",
+    "4": "Sexual Assault",
+    "5": "Violent Crime",
+    "6": "Terrorist Attacks",
+    "7": "Counterterrorism",
+    "8": "Smoking",
+    "9": "Vaping",
+    "10": "Tobacco Use",
+    "11": "Military Conflict",
+    "12": "War",
+    "13": "International Relations",
+    "14": "Pandemic",
+    "15": "Vaccines",
+    "16": "Health Guidelines",
+    "17": "COVID-19 News",
+    "18": "Cybersecurity",
+    "19": "Hacking",
+    "20": "Malware",
+    "21": "Addiction",
+    "22": "Substance Abuse",
+    "23": "Rehabilitation",
+    "24": "Hate Speech",
+    "25": "Offensive Language",
+    "26": "Discrimination",
+    "27": "Racism",
+    "28": "Homophobia",
+    "29": "Accidents",
+    "30": "Disasters",
+    "31": "Public Safety",
+    "32": "Weapons",
+    "33": "Gun Control",
+    "34": "Firearms",
+    "35": "Death"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Accidents": 29,
+    "Addiction": 21,
+    "Adult Content": 2,
+    "COVID-19 News": 17,
+    "Counterterrorism": 7,
+    "Crime": 3,
+    "Cybersecurity": 18,
+    "Death": 35,
+    "Disasters": 30,
+    "Discrimination": 26,
+    "Erotica": 1,
+    "Firearms": 34,
+    "Gun Control": 33,
+    "Hacking": 19,
+    "Hate Speech": 24,
+    "Health Guidelines": 16,
+    "Homophobia": 28,
+    "International Relations": 13,
+    "Malware": 20,
+    "Military Conflict": 11,
+    "Offensive Language": 25,
+    "Pandemic": 14,
+    "Pornography": 0,
+    "Public Safety": 31,
+    "Racism": 27,
+    "Rehabilitation": 23,
+    "Sexual Assault": 4,
+    "Smoking": 8,
+    "Substance Abuse": 22,
+    "Terrorist Attacks": 6,
+    "Tobacco Use": 10,
+    "Vaccines": 15,
+    "Vaping": 9,
+    "Violent Crime": 5,
+    "War": 12,
+    "Weapons": 32
+  },
+  "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": "4.44.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c8c1cf03c6864b2956e5235f34b02bcd3ea51f808ba94f5e30e78c84d468bb
+size 267937160

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9a68dcb35447df75f0612c9054154ae4966d21ea11f108d3320c9e29bf8278
+size 5112