add model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "configs/bert_config_v14.json",
+  "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": "4.22.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results_mlm.txt

@@ -0,0 +1 @@
+perplexity = 45.885502854818924

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c3cac73553a3cefd2124664304313d0efb09dfc867bdafd941925fa4228b5f
+size 273722207

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

train_results.txt

@@ -0,0 +1,5 @@
+epoch = 10.65
+train_loss = 3.6746194780010343e-06
+train_runtime = 301.9815
+train_samples_per_second = 423867.085
+train_steps_per_second = 1655.731

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230a6affa1bd54097d5941d6870f129df3cebd09e381914f5b96497ca3944f1d
+size 3439