Training in progress, step 5000

config.json

@@ -19,7 +19,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.15.0",
+  "transformers_version": "4.33.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 42000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce006fa7553f482060b398eeecbb1b3f6c042ecb9a48ba52ae2b684affbc688e
-size 470916529
+oid sha256:3982ac7fc55b9715bcdb04757a3ccfbf4379d3e15414d984be47c39ebc1f5eb5
+size 470900905

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1,13 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "HooshvareLab/bert-fa-zwnj-base", "tokenizer_class": "BertTokenizer"}
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48cbc16d272585c613876d7d993c0df7d1fe1a3a24a0197ac90ff8ff0fd942ab
-size 2927
+oid sha256:5bbf7ffb7aa6ab958f858552d42ec942c73a29a4281b5c5cfa38e18a9e2af350
+size 4027