finetuned version of bert-base-uncased on hateful / harmful meme texts

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-hateful-memes-expanded
+  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-hateful-memes-expanded
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on texts from the following datasets:
+- [Hateful Memes](https://hatefulmemeschallenge.com/), `train`, `dev_seen` and `dev_unseen`
+- [HarMeme](https://github.com/di-dimitrov/harmeme), `train`, `val` and `test`
+- [MultiOFF](https://github.com/bharathichezhiyan/Multimodal-Meme-Classification-Identifying-Offensive-Content-in-Image-and-Text), `Training`, `Validation` and `Testing`
+
+It achieves the following results on the evaluation set:
+- Loss: 3.7600
+
+## 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: 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.11.0
+- Pytorch 1.8.1+cu102
+- Datasets 1.8.0
+- Tokenizers 0.10.2

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2506ad026e163072933328a4acbf710b4504407932ebff3665fae29a81a6b9b
+size 438147282

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f53f22a601e5a4d83cefd6cc4d2ef95fb792635d2360297637158068679d14
+size 2863