Training in progress, epoch 1

config.json

@@ -1,24 +1,26 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForMaskedLM"
+    "BertForMaskedLM"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003565c0ed36cf8bd6aef9c213972d116fddc21f8c908b1623622d5f3757faf0
-size 267976815
+oid sha256:2ac55a5aadc8604785a06e8c4ed723556510e03c30bd76b763897011e49181e2
+size 438128811

runs/Apr21_03-20-48_a536b8a6346e/1650511255.5253513/events.out.tfevents.1650511255.a536b8a6346e.1797.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b11dfdcfb1d2d61e9abc102b633eb7dbaa40c9a6c144817f5fdedd81637bc293
+size 4912

runs/Apr21_03-20-48_a536b8a6346e/events.out.tfevents.1650511255.a536b8a6346e.1797.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20411b7bcfeb169177f2d078dd404fc6d112495b9442b174a5cd82c9e6e3bce8
+size 13027

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13683166445a9ab460a0388c6ba5e1d39938e9609562637cadb2ba109835e0b1
+oid sha256:4ce9fe3d5ceee5b62f0a18e0b3af49b202ccb4f19a320c961d1ead51497cc0ff
 size 3119