Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "google-bert/bert-base-chinese",
   "_num_labels": 2,
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -26,11 +26,16 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 21128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79190490ce435464ca752f47670e1909767efc7cb40a00eddd3a040649a0e0c
-size 437958648
+oid sha256:4758b9534bca0617c046b6f09feff9bb335e71420625cf51b29f5015e8b9c62e
+size 409100240

runs/Aug26_12-47-43_gaurav-gaudi-pod/events.out.tfevents.1724676547.gaurav-gaudi-pod.114636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e119f9d760b859dd331187d807d3250b077d2b8c88e4111ec7dd61985e1598c
+size 5537

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8528ec44d41d506dc82f0637ca048b8fa5c39e9fc05601d7bf1ee86eea04511
+oid sha256:c92af0d7d727e7c332facaa37b0b1165e8fdd8d26205e7a6e9950e892468d245
 size 4856