commit from quincyqiang

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 100.0,
+    "init_mem_cpu_alloc_delta": 324872,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 408400896,
+    "init_mem_gpu_peaked_delta": 0,
+    "perplexity": 4.663977352453378,
+    "train_mem_cpu_alloc_delta": 1622129,
+    "train_mem_cpu_peaked_delta": 68939497,
+    "train_mem_gpu_alloc_delta": 1641378304,
+    "train_mem_gpu_peaked_delta": 6652795904,
+    "train_runtime": 40107.6334,
+    "train_samples_per_second": 4.48
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "XiaobuBert",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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",
+  "transformers_version": "4.4.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 20710
+}

eval_results.json

@@ -0,0 +1,3 @@
+{
+    "perplexity": 4.663977352453378
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae73c3ba3eb93b865561f5bbf8de0dd9e35b2126ddd3c0b5738e61c775be6557
+size 407965586

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, "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": "XiaobuBert", "do_basic_tokenize": true, "never_split": null}

train_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 100.0,
+    "init_mem_cpu_alloc_delta": 324872,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 408400896,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 1622129,
+    "train_mem_cpu_peaked_delta": 68939497,
+    "train_mem_gpu_alloc_delta": 1641378304,
+    "train_mem_gpu_peaked_delta": 6652795904,
+    "train_runtime": 40107.6334,
+    "train_samples_per_second": 4.48
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d70b8677e87771be20aa9f28f3de175be2f36566b878e01865c74f4cf65338d
+size 2287