Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -7,22 +7,12 @@
   "attention_dropout": 0.1,
   "dim": 768,
   "dropout": 0.1,
-  "finetuning_task": "sst-2",
   "hidden_dim": 3072,
-  "id2label": {
-    "0": "NEGATIVE",
-    "1": "POSITIVE"
-  },
   "initializer_range": 0.02,
-  "label2id": {
-    "NEGATIVE": 0,
-    "POSITIVE": 1
-  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
-  "output_past": true,
   "pad_token_id": 0,
   "problem_type": "single_label_classification",
   "qa_dropout": 0.1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60475501eca7a3d6aac5e499059eb15518ef3826f952315a03cdbdc6ade22818
+oid sha256:b0edd6ce4b41c32bc02ebc1d2b2714eaa238bd8a9863b41bae0b61519ed73004
 size 267854321

tokenizer_config.json

@@ -1,11 +1,9 @@
 {
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
-  "never_split": null,
+  "name_or_path": "distilbert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cdda410b39a44df892cb1ca5e99c45457d598b2bc196a95b57367599d0ed9e1
+oid sha256:8ee423264dfe12960bbfbb1af259dbc2539efa633cc9f61e7cc447d20722fbfe
 size 3311