Jairnetojp/content-moderation-v1

README.md

@@ -0,0 +1,64 @@
+---
+base_model: Jairnetojp/content-moderation
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: bert-finetuned-sem_eval-english
+  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-finetuned-sem_eval-english
+
+This model is a fine-tuned version of [Jairnetojp/content-moderation](https://huggingface.co/Jairnetojp/content-moderation) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2343
+- F1: 0.5458
+- Roc Auc: 0.7829
+- Accuracy: 0.4655
+
+## 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: 128
+- eval_batch_size: 128
+- 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 | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| No log        | 1.0   | 232  | 0.2283          | 0.5361 | 0.7829  | 0.4503   |
+| No log        | 2.0   | 464  | 0.2343          | 0.5458 | 0.7829  | 0.4655   |
+| 0.069         | 3.0   | 696  | 0.2461          | 0.5392 | 0.7832  | 0.4544   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Jairnetojp/content-moderation",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Doxxing",
+    "1": "Profanity",
+    "2": "Grooming",
+    "3": "CSAMDiscussion",
+    "4": "Toxic",
+    "5": "Bullying",
+    "6": "Sexual",
+    "7": "Hate",
+    "8": "SelfHarm",
+    "9": "Radical",
+    "10": "Threat",
+    "11": "Insult",
+    "12": "VulgarName",
+    "13": "PII",
+    "14": "Blocked"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Blocked": 14,
+    "Bullying": 5,
+    "CSAMDiscussion": 3,
+    "Doxxing": 0,
+    "Grooming": 2,
+    "Hate": 7,
+    "Insult": 11,
+    "PII": 13,
+    "Profanity": 1,
+    "Radical": 9,
+    "SelfHarm": 8,
+    "Sexual": 6,
+    "Threat": 10,
+    "Toxic": 4,
+    "VulgarName": 12
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56fbe9e2bfc52901e8695f7587c08611a9c4b3ba0f71eb712f00b7d2ef7d9ed
+size 541357364

runs/Mar10_20-04-57_a5a2f8f00184/events.out.tfevents.1710101106.a5a2f8f00184.398.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50124af7e18c86347cc8dd2226b04f579f20bff225540095fecb0fea928ae1d7
+size 7061

runs/Mar10_20-04-57_a5a2f8f00184/events.out.tfevents.1710101782.a5a2f8f00184.398.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9feb5e9af04e9b30d9b3752c5e9d60b0f6f7e4faaa181792e245768e07f0f56
+size 508

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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]",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47dcb04585bfa51bc8a6b978a20bfb68324e8965313e07336766dad83a36060
+size 4920