Training in progress, step 10000

config.json

@@ -0,0 +1,23 @@
+{
+  "activation": "relu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.005,
+  "dim": 768,
+  "dropout": 0.005,
+  "embedding_size": 128,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "hybridbert",
+  "n_heads": 12,
+  "n_layers": 12,
+  "pad_token_id": 0,
+  "qa_dropout": 0.005,
+  "seq_classif_dropout": 0.005,
+  "sinusoidal_pos_embds": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c3135dcf917bdcc865b4edc75a2c49d96a4e6f08fd19e30ce93037929f5d29
+size 406664909

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 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651a6f1c3072e2bae1473f2fec118baeaee1bf7bd84d332c26afb4434aed6e73
+size 5179