Training in progress, epoch 1

config.json

@@ -1,10 +1,13 @@
 {
-  "_name_or_path": "HooshvareLab/bert-fa-base-uncased",
+  "_name_or_path": "dadashzadeh/roberta-sentiment-persian",
   "architectures": [
-    "BertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "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": 768,
@@ -16,21 +19,21 @@
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
+    "negative": 0,
+    "neutral": 2,
+    "positive": 1
   },
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 100000
+  "vocab_size": 42000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c4947ac8b8a5ed9ec97286b130d2ace2d95c6d077f7d4478f8f3227b328fdd
-size 651398148
+oid sha256:647a7e686da6a511f9969a53dd57b49bf9ec1892f1760441b76aa5b374ba8ea6
+size 473225820

runs/Oct11_06-12-39_b0be7e6222f4/events.out.tfevents.1728627173.b0be7e6222f4.1498.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417eebc9db94525f6dbd739e1fe8ce6ad1b4aa973b38e34eb129daaa93ce4152
+size 5584

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e194335e30fa902a6cbb946bf2c5b56f2188c166da26168a6d0ce16c3bb1f05
+oid sha256:1dc428ddc6985bc0d5694b81f848fd9166ca5218c48cc8bf421acee8f2c8bb6c
 size 5176