Training in progress, epoch 1

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "pedramyazdipoor/persian_xlm_roberta_large",
+  "_name_or_path": "dadashzadeh/roberta-sentiment-persian",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -10,27 +10,24 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "Negative",
     "1": "Positive",
     "2": "Neutral"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
+    "negative": 0,
+    "neutral": 2,
+    "positive": 1
   },
-  "language": "english",
-  "layer_norm_eps": 1e-05,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "name": "XLMRoberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -38,5 +35,5 @@
   "transformers_version": "4.44.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 42000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6f504c89e40e2d97442bd92bd347079ac08915f380ecba88fbb51e5e0742df
-size 2239622772
+oid sha256:102cb07e7094dd45e22920983ad13f88d3533756792d7d703e3dcd075330b134
+size 473225820

runs/Sep15_04-12-29_1ea3fea1e80a/events.out.tfevents.1726373560.1ea3fea1e80a.1157.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56865d14741d7df039d9f8e5841c50732ccc908fbe9a4dae17a1b68a3c18c1e2
-size 6875
+oid sha256:be4d4e3c3411997ddb6368e5a875e225ae2541ddb29f6b19b23938bfc32ae499
+size 7666

runs/Sep15_04-37-54_1ea3fea1e80a/events.out.tfevents.1726375086.1ea3fea1e80a.8430.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dc52df591f98d84e8a1e53673e79f0328b34792b727a74c1c55d56983d75ef
+size 5217

runs/Sep15_04-39-05_1ea3fea1e80a/events.out.tfevents.1726375154.1ea3fea1e80a.8430.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a6190c8a349602ee1b4aaa77a15ef7093992b8bbdabb740380924386bd2565
+size 5215

runs/Sep15_04-39-28_1ea3fea1e80a/events.out.tfevents.1726375177.1ea3fea1e80a.8430.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4aa6ac739040a655c5ab729f953e2b83f784389eb9e8391b06186f95030851
+size 5795

special_tokens_map.json

@@ -2,27 +2,27 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "cls_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
     "content": "<mask>",
-    "lstrip": false,
+    "lstrip": true,
     "normalized": false,
     "rstrip": false,
     "single_word": false
@@ -30,21 +30,21 @@
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6247be075973430c70e5980bd5af624466882ca896e8994078f6707661e890ca
-size 17082898
+oid sha256:ad6ff9d8d4dfc5111a9e2e3bf6cd868a97c6e54c84fab43ddba87ef05c541607
+size 2749245

tokenizer_config.json

@@ -1,9 +1,10 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -11,7 +12,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -19,7 +20,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -27,38 +28,82 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
+    "4": {
       "content": "<mask>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "5": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<nl>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<hs>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_lower_case": false,
   "eos_token": "</s>",
-  "full_tokenizer_file": null,
+  "errors": "replace",
   "mask_token": "<mask>",
-  "max_length": 32,
+  "max_length": 512,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "</s>",
-  "sp_model_kwargs": {},
   "stride": 0,
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
   "truncation_side": "right",
-  "truncation_strategy": "only_first",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8658cf6fac6cb7a55a3eed540a2b8ce79ee7b429656c925aae4aa317e284cd
+oid sha256:b684b44b2219b673134d95e5c6eef13f43a43426f0e413160c5be100398b6b93
 size 5176