Training in progress, step 500

config.json

@@ -1,13 +1,12 @@
 {
+  "activation": "gelu",
   "architectures": [
-    "BertForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "O",
     "1": "B-PER",
@@ -24,7 +23,6 @@
     "12": "I-CW"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "B-CORP": 5,
     "B-CW": 11,
@@ -40,16 +38,17 @@
     "I-PROD": 10,
     "O": 0
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.50.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a4cb0d368bbb9ee55d932583cee162a3d1fdf637038c258dab710838fed022
-size 430942044
+oid sha256:4c59c1f6c1baa5d87f34706fa503675cf64ba5f577e8f12a29dbd813a8dfa85c
+size 260815972

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf19e2e6934fe079f7923baa254f4e188092dbe0a85edb74a6f3fba62500271
+oid sha256:254d8d413c0918b0fa2dfcdd6d916889dd5a0fee46b9784e6107a0476dfe3144
 size 5304