Training in progress, step 16

config.json

@@ -2,7 +2,7 @@
   "_name_or_path": "distilbert/distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
-    "DistilBertForMaskedLM"
+    "DistilBertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "dim": 768,
@@ -14,10 +14,12 @@
   "n_heads": 12,
   "n_layers": 6,
   "pad_token_id": 0,
+  "problem_type": "single_label_classification",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
+  "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3196bf59b9caa261e9db9c0d3ab35137d7b3f98b0bff544193b460d533d77617
-size 265473108
+oid sha256:134124f4dac0786eb5d58a71a8cfd513525f081eb7ff51c9a04cd094f55e3c4f
+size 267832560

runs/Sep26_17-53-19_b1933b188e2f/events.out.tfevents.1727373201.b1933b188e2f.772.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd1579a23dd04c02be7062ea9947db92c202d6e63ae5e09fab4a8291852441d
+size 5511

tokenizer_config.json

@@ -43,9 +43,11 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
+  "never_split": null,
   "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 sha256:41a9577fe8243d6ddd6dca22d78a6cf21932b3d5c5feae32aa2627e31c940842
+oid sha256:2dd72675a1187656d30b94eccbbbf4a3cc17be52c2cb888d45a3b971ce2c7a97
 size 5240