Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -7,6 +7,7 @@
   "attention_dropout": 0.1,
   "dim": 768,
   "dropout": 0.1,
+  "finetuning_task": "sst-2",
   "hidden_dim": 3072,
   "id2label": {
     "0": "NEGATIVE",
@@ -21,6 +22,7 @@
   "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 sha256:7d2e88deee567553a76e8f9d42ddbc2140da8ba667ce5b8c6d2e265da896e121
+oid sha256:3cd38220ad7da7690d0b59ae6c0129d84e7a1f75436f2ec4ec818100784b77b4
 size 267854125

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047ec55a46a3357fa64f0f2b1e1091b128bce1bc69528f637d2796478e48d28d
+oid sha256:a22f3e92cace10e3d68ccfea7c8a118fd93a857c448df33c4a572fb728755124
 size 3579