Training in progress, epoch 0

config.json

@@ -1,37 +1,32 @@
 {
-  "_name_or_path": "qarib/bert-base-qarib_far_9920k",
+  "_name_or_path": "aubmindlab/bert-large-arabertv02-twitter",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
-    "0": "request",
-    "1": "complaint",
-    "2": "satisfaction"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
-    "complaint": 1,
-    "request": 0,
-    "satisfaction": 2
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "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",
   "torch_dtype": "float32",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b92c28258544157e3574cc4a82f19ab42c770ffb94165b3f06441bcd848fdaa1
-size 540855413
+oid sha256:709dfbb5bfc4338d93bcf9ba6129d6c067f3eb7a8429e44ec4ca63052e914cbd
+size 1477844597

runs/Jun11_17-56-53_35ea9e197b6c/events.out.tfevents.1686506232.35ea9e197b6c.5859.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8757222ae32c5bbf62dd15a610ccea018c6d99dd8a4fdf5a9170a0498060c965
+size 4607

tokenizer_config.json

@@ -2,14 +2,20 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "[بريد]",
+    "[مستخدم]",
+    "[رابط]"
+  ],
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "unk_token": "[UNK]",
+  "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535f8928bcef1d99116ae562bd9eafbadec13b0f8d2d5fb2deb024ace97e21a0
+oid sha256:15b276cad04a08b5726b113ede2970a0bd785db37346244d5ce122f33977325b
 size 3963