Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google-bert/bert-base-chinese",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "_num_labels": 2,
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -26,16 +26,11 @@
   "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": 21128
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75b83f86e40b4c7d3996b870f71e1104d21232ead61c921277576b69e47c704e
-size 409100240
+oid sha256:a429f33d67eda865c2cfb8724c26278bce145f0b76f50e6a706cd52bb345efe5
+size 437958648

runs/Aug26_13-18-37_gaurav-gaudi-pod/events.out.tfevents.1724678362.gaurav-gaudi-pod.123490.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75ef2e6a2ce074db53b0805c3087a27f8ec2af27a3900eb8fb9ad4cda51a90c
+size 5381

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "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:c92af0d7d727e7c332facaa37b0b1165e8fdd8d26205e7a6e9950e892468d245
+oid sha256:ba1403d4530080a46290257de5071bd39e49218f4185c624362f0e4389ebed3d
 size 4856