Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -7,12 +7,22 @@
   "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55dc9eadee166399d97bb7323ea9c3cc1da38eb3bf2437bd71658f1aafaef8de
+oid sha256:cb6440e2d71c11d338f7bcc1497e6eab77ce87e390a0d03ed50f76a887f7fa71
 size 267832560

tokenizer_config.json

@@ -43,9 +43,11 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,