Training in progress, epoch 1

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "bert-base-multilingual-cased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "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-corporation",
@@ -17,7 +16,6 @@
     "4": "I-person"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "B-corporation": 1,
     "B-person": 3,
@@ -25,21 +23,16 @@
     "I-person": 4,
     "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,
   "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "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": "4.33.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b95e29aef9b8973894f34a32345ac7fef0cb6645cb7f0b6e26c7df4218a6aa
-size 709134505
+oid sha256:04255bebfc4d7c2075fbe2d1a7357a0f123d8097d90bebe04f44cc8a5a0a8758
+size 265501733

tokenizer_config.json

@@ -1,16 +1,13 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_len": 512,
   "model_max_length": 512,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b93ba0beb90cbd54e6ea0d80b0e26ffdd9afd04db0832828df83bd8f0ec8b0
+oid sha256:33bf887705d433d12e536dd9b4b12e06c73d4960fc9bfa755b6495a55f261a2f
 size 4027