Training in progress, epoch 1

config.json

@@ -4,8 +4,6 @@
   ],
   "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,
@@ -27,16 +25,11 @@
   "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",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.53.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 100000
+  "vocab_size": 64000
 }

eval_metrics.json

@@ -1,9 +1,9 @@
 {
-  "eval_loss": 0.6485912203788757,
-  "eval_accuracy": 0.7111756168359942,
-  "eval_macro_f1": 0.6882835055560014,
-  "eval_runtime": 4.7614,
-  "eval_samples_per_second": 289.409,
-  "eval_steps_per_second": 9.241,
+  "eval_loss": 0.6449292898178101,
+  "eval_accuracy": 0.7075471698113207,
+  "eval_macro_f1": 0.6866383431751671,
+  "eval_runtime": 4.7701,
+  "eval_samples_per_second": 288.886,
+  "eval_steps_per_second": 9.224,
   "epoch": 5.0
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19524b563dc1ed22bd407455d126b1039f4a3ef4ccfdfc340fe4058ef32f92f1
-size 651398148
+oid sha256:1cf940a7cee9e6e51ffb67f69182b9174cbb9e9d1e7782b95d76c959973d41e5
+size 540806148

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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

@@ -39,16 +39,45 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "5": {
+      "content": "[رابط]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "6": {
+      "content": "[بريد]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "7": {
+      "content": "[مستخدم]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "extra_special_tokens": {},
   "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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20fa97b9af029ef95d603867b8cd7527cfbcdba3983855798197163f1ee90e2
+oid sha256:90c703a0884f47ca6e5a44781d5a46def7f0d6f441cb74024a4c6b3120ac1651
 size 5368