Training in progress, epoch 1

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "allenai/scibert_scivocab_uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "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-DatasetName",
@@ -26,7 +26,6 @@
     "14": "I-TaskName"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "B-DatasetName": 1,
     "B-HyperparameterName": 3,
@@ -44,16 +43,16 @@
     "I-TaskName": 14,
     "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,
-  "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": "4.34.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 31090
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:658c2cfa5bec7bb7271ff8009eb85fdb0cf0deb46445e7b4bdf04021b5a5d64a
-size 437425830
+oid sha256:91ada7b42a47714c29e8b24d6cd9c76ad7ff295f9c2719dce923ffa3d007f80c
+size 265533026

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",
@@ -9,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "101": {
+    "100": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -17,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -25,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -33,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "104": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -44,15 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "model_max_length": 512,
   "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 sha256:59e25fcf10b6bd9a934d8833eff1a68eb7b2e36fa44c5ce8f1509c9d0536b192
+oid sha256:9e9c0831c4d9b56a7c93ac0a29b58301e7ffaa07fdf845a4474106f4c8855eb7
 size 4536