Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "distilbert/distilbert-base-cased-distilled-squad",
   "activation": "gelu",
   "architectures": [
     "DistilBertForQuestionAnswering"
@@ -13,12 +13,13 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
+  "sinusoidal_pos_embds": true,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.0.dev0",
-  "vocab_size": 30522
+  "transformers_version": "4.38.1",
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35baa3b45f8f97b71800d5be5d041b6e686a4b6a86d3e79f47e9ddf4735e0fa7
-size 265470032
+oid sha256:f29062f80baf8d8aaf99f8bf3c8ef36277b7940a0f7d8e18ecfe0e6b7212622f
+size 260782152

tokenizer_config.json

@@ -43,9 +43,9 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43801b41b3aa1a0e1a94a28aed902a5580a617f801f3266c353410a27623144d
+oid sha256:b061823bd28c23d56978f91b9c0480759d2c3d8b70a67aa016ae2a34d789e474
 size 4920