MASRIBERTv2 — continued pretraining (ppl=15.87)

config.json

@@ -0,0 +1,36 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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",
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 100000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abbb0b44c52db25c0b965ece5707dbc709d5d01caee95aa78b18a2b25e69fc2
+size 959395416

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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:d55404c70265aef200d4d9d4931ded1d307e224fa4fec3835f40df1d53a7f0ff
+size 5201

training_metadata.json

@@ -0,0 +1,35 @@
+{
+  "base_model": "T0KII/MASRIBERT",
+  "grandparent_model": "UBC-NLP/MARBERTv2",
+  "version": "v2",
+  "new_data_sources": [
+    "faisalq/EFC-mini",
+    "MBZUAI-Paris/Egyptian-SFT-Mixture"
+  ],
+  "v1_data_sources": [
+    "hard",
+    "ar_res_reviews",
+    "arbml/TEAD",
+    "AOC_youm7_comments",
+    "RestOf_AOC_youm7_comments",
+    "Egyptian_Tweets",
+    "TaghreedT",
+    "TE_Telecom",
+    "TE_Tweets"
+  ],
+  "block_size": 64,
+  "mlm_probability": 0.2,
+  "whole_word_mask": true,
+  "learning_rate": 2e-05,
+  "epochs": 2,
+  "effective_batch_size": 128,
+  "train_blocks": 1849729,
+  "eval_blocks": 18685,
+  "final_eval_loss": 2.764298439025879,
+  "final_perplexity": 15.867903782671096,
+  "intended_downstream_tasks": [
+    "sentiment_analysis",
+    "emotion_classification",
+    "sarcasm_detection"
+  ]
+}