Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_name_or_path": "distilbert/distilbert-base-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForQuestionAnswering"
@@ -13,6 +13,7 @@
   "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,
@@ -20,5 +21,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.1",
-  "vocab_size": 30522
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d2d9f6c6916f2c5b95b0e7f7f85ca397219a5192226829c1098a248c634c3c
-size 265470032
+oid sha256:d8cfbe295c10bb916ab7d850b7904c8ab96b4b6e8cb7189f2e21356cf1b13f5a
+size 260782152

runs/Jun05_01-53-01_2764dce19e75/events.out.tfevents.1717552382.2764dce19e75.34.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65aaff48fc7007be8c220ac4c89d198ffb291f7f388a83d413acdcf674ec6d60
+size 5222

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f177fc6e1cf23db1a0cd9f9964855c282c349341b01f9aa666a3265700298086
+oid sha256:2d0c6a6d6ed1481bbb83e65d85fa08e0948e4377736810adeb056b72d7edf889
 size 5112