Enable output_hidden_states

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "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": "LABEL_0",
     "1": "LABEL_1",
@@ -28,7 +28,6 @@
     "16": "LABEL_16"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -48,15 +47,16 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "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_hidden_states": 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,
   "transformers_version": "4.3.3",
-  "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 sha256:93a6239c122d4f594523e15c6e10cdb4e96e770279f4b2841c5f52db7b85b105
-size 435707447
+oid sha256:8c272cc44474786213010e81d00100f6d6a248690e8b3fc6062bf3950b63d57e
+size 265546245

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "distilbert-base-uncased"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73cb402c00369cfb109cb276f48af4cf19d94356aac25e6014519427294815e
+oid sha256:44673731fe36c8974d5e12d818a9c3c6081159e4481705fac8b32eb21c9791c1
 size 2159