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 sha256:9ca10eaf16389ad4ea9e1cef2fdfd108f90c2ab447ba34f5039a82793b699b71
+oid sha256:0f3ef1b18fedc0eefac6e70ffb042ac39dc8169bd2b9c0b6639589ec08949e28
 size 267854125

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac2e5e5ec9c43d90a904cbeec20fc3cd51dcdecdba43f78932c15fdb027f596
+oid sha256:41cd224f975e8d8d522087b95ec83b83187308e75ab7aca359181f96cbf448dc
 size 3579