Training in progress, epoch 0

config.json

@@ -1,41 +1,39 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "aubmindlab/bert-large-arabertv02-twitter",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "id2label": {
-    "0": "Positive",
-    "1": "Negative",
-    "2": "Neutral",
-    "3": "Mixed"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
   },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "label2id": {
-    "Mixed": 3,
-    "Negative": 1,
-    "Neutral": 2,
-    "Positive": 0
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 64000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e641ef208c797251140016230a92889e1abc07a0c0d4bae12996490fec5b4d
-size 2239713713
+oid sha256:cccb059e6cccf109653a1efed846498e5d91c106db6664591e48d1b192e8d98a
+size 1477844273

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d47d70b1d07d7f6501cd84458cd4d9cfbdec4893d78ad9f7a6238e29a88d87d
+oid sha256:0f851a6a917ebee107844130443bce2e5908f8d601ddef94dfda43743bd1fd2a
 size 4091