Training in progress, epoch 1

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "B-corporation",
@@ -24,6 +25,7 @@
     "12": "I-product"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "B-corporation": 1,
     "B-creative-work": 3,
@@ -39,16 +41,16 @@
     "I-product": 12,
     "O": 0
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7a6b7a1cb6581e3aaa94dd6718aa6ca3ccb1d254cc931ef5fdab7a0cf57854
-size 265526309
+oid sha256:860273b961900dc28c92b487102508387f5072027e71be133454699b58b0c359
+size 1336560621

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce579e9e7b44ea19de99044c90f225fed0233c691ce89a9a87ad9a5dae408dbd
+oid sha256:e6188cf62d52fa7fef646992d116ea376db31953f9504f7b22b1ea74476d7ff5
 size 3451