Uploading Hate Speech Detection

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: distilbert/distilbert-base-uncased
+license: mit
+base_model: neuralmind/bert-large-portuguese-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hate_speech_detection_with_target-bert-large-portuguese-cased
 
-This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0757
-- Accuracy: 0.9851
+- Loss: 0.0610
+- Accuracy: 0.9892
 
 ## Model description
 
@@ -50,26 +50,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2915        | 1.0   | 93   | 0.7033          | 0.7618   |
-| 0.6165        | 2.0   | 186  | 0.4898          | 0.8051   |
-| 0.3604        | 3.0   | 279  | 0.1346          | 0.9621   |
-| 0.0855        | 4.0   | 372  | 0.0436          | 0.9865   |
-| 0.0228        | 5.0   | 465  | 0.0707          | 0.9838   |
-| 0.0168        | 6.0   | 558  | 0.0737          | 0.9838   |
-| 0.0132        | 7.0   | 651  | 0.0717          | 0.9865   |
-| 0.0074        | 8.0   | 744  | 0.0871          | 0.9851   |
-| 0.0069        | 9.0   | 837  | 0.0599          | 0.9892   |
-| 0.0021        | 10.0  | 930  | 0.0684          | 0.9878   |
-| 0.0033        | 11.0  | 1023 | 0.0726          | 0.9865   |
-| 0.0028        | 12.0  | 1116 | 0.0794          | 0.9865   |
-| 0.001         | 13.0  | 1209 | 0.0743          | 0.9865   |
-| 0.0016        | 14.0  | 1302 | 0.0671          | 0.9865   |
-| 0.0007        | 15.0  | 1395 | 0.0752          | 0.9851   |
-| 0.0005        | 16.0  | 1488 | 0.0747          | 0.9851   |
-| 0.0006        | 17.0  | 1581 | 0.0757          | 0.9851   |
-| 0.0004        | 18.0  | 1674 | 0.0758          | 0.9851   |
-| 0.0004        | 19.0  | 1767 | 0.0756          | 0.9851   |
-| 0.0004        | 20.0  | 1860 | 0.0757          | 0.9851   |
+| 0.8021        | 1.0   | 93   | 0.1410          | 0.9594   |
+| 0.0974        | 2.0   | 186  | 0.0974          | 0.9770   |
+| 0.1401        | 3.0   | 279  | 0.0550          | 0.9838   |
+| 0.046         | 4.0   | 372  | 0.0618          | 0.9878   |
+| 0.0344        | 5.0   | 465  | 0.0469          | 0.9892   |
+| 0.2429        | 6.0   | 558  | 0.0854          | 0.9878   |
+| 0.0696        | 7.0   | 651  | 0.0451          | 0.9892   |
+| 0.0394        | 8.0   | 744  | 0.0460          | 0.9892   |
+| 0.0279        | 9.0   | 837  | 0.0469          | 0.9892   |
+| 0.0362        | 10.0  | 930  | 0.0779          | 0.9865   |
+| 0.0215        | 11.0  | 1023 | 0.0655          | 0.9878   |
+| 0.0193        | 12.0  | 1116 | 0.0587          | 0.9892   |
+| 0.0154        | 13.0  | 1209 | 0.0594          | 0.9892   |
+| 0.015         | 14.0  | 1302 | 0.0601          | 0.9905   |
+| 0.0156        | 15.0  | 1395 | 0.0604          | 0.9892   |
+| 0.0157        | 16.0  | 1488 | 0.0604          | 0.9892   |
+| 0.0145        | 17.0  | 1581 | 0.0607          | 0.9892   |
+| 0.0176        | 18.0  | 1674 | 0.0607          | 0.9892   |
+| 0.0193        | 19.0  | 1767 | 0.0609          | 0.9892   |
+| 0.0206        | 20.0  | 1860 | 0.0610          | 0.9892   |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
   "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",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
     "0": "gay people non-hateful",
     "1": "gay people hateful",
@@ -27,6 +28,7 @@
     "15": "unknown hateful"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "black people hateful": 9,
     "black people non-hateful": 8,
@@ -45,17 +47,23 @@
     "women hateful": 7,
     "women non-hateful": 6
   },
+  "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,
+  "output_past": true,
   "pad_token_id": 0,
+  "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",
   "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": "4.48.1",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f35320ff765895ada82199fb314e7916e9883c7cda8cbc0b6e9eeb5981ec5e8
-size 267875632
+oid sha256:3b0420c000ef87d3e9328bceab297bce05ad420a8fb1682cac5af6e6aa5fcd12
+size 1337698272

tokenizer_config.json

@@ -41,16 +41,18 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "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:dfa687e3f418911ae80636ed846f2d9a449f6efc1921bc2d296fb66c6b43f40a
+oid sha256:841b22bc60db7f01f6cca60f4f27808415b6907d98773e38ed24fc9cca628477
 size 5432