Training in progress, epoch 1

config.json

@@ -1,33 +1,36 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "HooshvareLab/bert-fa-base-uncased-sentiment-snappfood",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "snappfood",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "NEGATIVE",
     "1": "POSITIVE"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "NEGATIVE": 0,
     "POSITIVE": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.33.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c43a82f286a6d6d74d9e1dbb0b62da53c3f3ac5d44de0719467cd55589eb6fb
-size 267855533
+oid sha256:0d12b45353f0ac1e7648f099313ec924c1a2d08e07cd75bb8821b67452c5e7f2
+size 651439921

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ca9e9e0f8d17d6d01ab24f24313b0ea0e917e0e7e6d0e4ceb0072faf468b13
+oid sha256:b1b03559d6acca8c9e091019ee4ee8d23ff97e43538dceeacafbfca3802b0953
 size 4027