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 = 19.53581151986937

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482f1b32396c2e19d849c6aea5199827dd9b71777f75611c1918c9cfef5b8825
+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 = 5.55
+train_loss = 2.416302919921875
+train_runtime = 186700.1564
+train_samples_per_second = 685.591
+train_steps_per_second = 2.678

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1868150a4eab05e586a119a8cd10eb296e9e7ea14d7b67502a5d90982441d876
+size 2863