add checkpoint

added_tokens.json

@@ -0,0 +1 @@
+{"[sys]": 30522, "[usr]": 30523}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-aipnlp/zengweihao02/PretrainModel/bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30524
+}

eval_results.txt

@@ -0,0 +1,2 @@
+loss = 0.5944646852357047
+perplexity = tensor(1.8121)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b08c3b744fc41f964231ff6d4f426f98aca82d717aeb56771089af3995ab6e
+size 438138598

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-aipnlp/zengweihao02/PretrainModel/bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f8b9accd1905ed4bf66efa676eb40d24e2860322de80fb0bcc555ca8f9f4d0
+size 2479