Training in progress, epoch 1

config.json

@@ -2,40 +2,19 @@
   "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "DistilBertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
-  "id2label": {
-    "0": "O",
-    "1": "B-PER",
-    "2": "I-PER",
-    "3": "B-ORG",
-    "4": "I-ORG",
-    "5": "B-LOC",
-    "6": "I-LOC",
-    "7": "B-MISC",
-    "8": "I-MISC"
-  },
   "initializer_range": 0.02,
-  "label2id": {
-    "B-LOC": 5,
-    "B-MISC": 7,
-    "B-ORG": 3,
-    "B-PER": 1,
-    "I-LOC": 6,
-    "I-MISC": 8,
-    "I-ORG": 4,
-    "I-PER": 2,
-    "O": 0
-  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8af12eb5a8f702b5eb5050494a80ef27c9298f96c171428c27ae6f17b06cade
-size 265491548
+oid sha256:03534919788ee2139aa59e01a765137c5e7691226586ed66acdba2a9a7581b98
+size 267832560

tokenizer.json

@@ -6,14 +6,7 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c07aa9011d183fc30eac19189ad9969d890aa099cbe8db74b5d89850ba2312
+oid sha256:dc768102761cb5a2d9e1ff9f4f180b9c3e33c79cfd54ceaa72a0b60ef908a8cf
 size 5304