add model

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "relative_key",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 30000
+}

eval_results_mlm.txt

@@ -0,0 +1 @@
+perplexity = 17.900050490733094

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e911e49aa9ca5c4b7e69c60f7789b9b15123f30eca387d2a7327f1769bd6dd
+size 267577631

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 @@
+{"mask_token": "[MASK]", "cls_token": "[CLS]", "unk_token": "[UNK]", "pad_token": "[PAD]", "sep_token": "[SEP]", "tokenizer_class": "PreTrainedTokenizerFast"}

train_results.txt

@@ -0,0 +1,5 @@
+epoch = 11.55
+train_loss = 2.541904963623047
+train_runtime = 186540.8186
+train_samples_per_second = 686.177
+train_steps_per_second = 2.68

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2ad0eb438830b963f10b24d09d991d8b70f5f39f41d51df21497f3bdb8bd87
+size 2863