Upload 10 files

added_tokens.json

@@ -1 +1 @@
-{"<BOS>": 28996, "<SEP>": 28998, "<PAD>": 28999, "<EOS>": 28997}
+{"<BOS>": 28996, "<EOS>": 28997, "<SEP>": 28998, "<PAD>": 28999}

eval_results_mlm.txt

@@ -1 +1 @@
-perplexity = 47.5140214816094
+perplexity = 12.60146402572349

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fbf5dab4a15412f879cef823c7c4640ff99951eadbf6f65cfd3e3376e18a82
-size 1334625493
+oid sha256:5ecdd9b300ca2ba4ce5c93d4f500b9a58e8121a5501ba44d1ef1aef7ef3a4c16
+size 1334625499

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<BOS>", "eos_token": "<EOS>", "unk_token": "[UNK]", "sep_token": "<SEP>", "pad_token": "<PAD>", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "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-large-cased"}
+{"do_lower_case": false, "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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-cased", "tokenizer_class": "BertTokenizer"}

train_results.txt

@@ -1,11 +1,11 @@
-epoch = 10.0
-init_mem_cpu_alloc_delta = 1168576512
-init_mem_cpu_peaked_delta = 1323925504
+epoch = 1.0
+init_mem_cpu_alloc_delta = 1168203776
+init_mem_cpu_peaked_delta = 1324277760
 init_mem_gpu_alloc_delta = 1335215616
 init_mem_gpu_peaked_delta = 0
-train_mem_cpu_alloc_delta = 54071296
-train_mem_cpu_peaked_delta = 356077568
+train_mem_cpu_alloc_delta = 31993856
+train_mem_cpu_peaked_delta = 0
 train_mem_gpu_alloc_delta = 4003456000
 train_mem_gpu_peaked_delta = 19106743296
-train_runtime = 980.3735
-train_samples_per_second = 0.785
+train_runtime = 81.7708
+train_samples_per_second = 0.942

trainer_state.json

@@ -1,29 +1,23 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
-  "global_step": 770,
+  "epoch": 1.0,
+  "global_step": 77,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 6.49,
-      "learning_rate": 3.506493506493507e-08,
-      "loss": 4.2363,
-      "step": 500
-    },
-    {
-      "epoch": 10.0,
-      "step": 770,
-      "total_flos": 6282413018234880.0,
-      "train_runtime": 980.3735,
-      "train_samples_per_second": 0.785
+      "epoch": 1.0,
+      "step": 77,
+      "total_flos": 628241301823488.0,
+      "train_runtime": 81.7708,
+      "train_samples_per_second": 0.942
     }
   ],
-  "max_steps": 770,
-  "num_train_epochs": 10,
-  "total_flos": 6282413018234880.0,
+  "max_steps": 77,
+  "num_train_epochs": 1,
+  "total_flos": 628241301823488.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d1f848dbe017c8469705d9ef92d62e3ed52b8479d6f13ba39a024dac0c5229
-size 2415
+oid sha256:b3d6af5026a1064f813958e7381618040be16d76b31c206f97f2cc7eb0afdcc1
+size 2351