Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -1,7 +1,8 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
-    "DistilBertModel"
+    "DistilBertForMaskedLM"
   ],
   "attention_dropout": 0.1,
   "dim": 768,
@@ -11,12 +12,13 @@
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,
-  "n_layers": 4,
+  "n_layers": 6,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
+  "transformers_version": "4.26.1",
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7232dc79925f1bd1219be3c340eb1f8d69b86be7f973304aa143d63f0b29c6
-size 208771005
+oid sha256:8f862edf708eebc7fcdf6e43c2aedc3421bd640d8f9b1bee656674f4ceded496
+size 267976561

special_tokens_map.json

@@ -1,9 +1,7 @@
 {
-  "bos_token": "<|BOS|>",
-  "cls_token": "<|CLS|>",
-  "eos_token": "<|EOS|>",
-  "mask_token": "<|MASK|>",
-  "pad_token": "<|PAD|>",
-  "sep_token": "<|SEP|>",
-  "unk_token": "<|UNK|>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,14 +1,14 @@
 {
-  "add_prefix_space": false,
-  "bos_token": "<|BOS|>",
-  "cls_token": "<|CLS|>",
-  "eos_token": "<|EOS|>",
-  "mask_token": "<|MASK|>",
-  "model_max_length": 1024,
-  "name_or_path": "gpt2",
-  "pad_token": "<|PAD|>",
-  "sep_token": "<|SEP|>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 66.0,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "special_tokens_map_file": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|UNK|>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3fa84723cc899fae0aa070f0eb821021ae4e9142ab251021c5a20073904b52
+size 3515