distil RoBERTa model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "distilroberta-base",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -11,22 +11,22 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "neutral",
-    "1": "positive",
-    "2": "negative"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "neutral": 0,
-    "positive": 1,
-    "negative": 2
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3b7a2ccac1c9b0211223a068211830cbdbfde0cceb24752d1984c45f7093a1
-size 498665141
+oid sha256:e939f34865e6847d37e29cbaa7398be45868730f558c2cb7b8dd1d5cce805c2e
+size 328522997

tokenizer_config.json

@@ -6,7 +6,7 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "roberta-base",
+  "name_or_path": "distilroberta-base",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "special_tokens_map_file": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368222b95b15604157afa1d409f4acb6777f76b06bcc5ebc28f6ddc38c76d764
+oid sha256:d6eb04bc1f47fbba36599c28631bd143c66a428e0986e8ba146a2fca51665e09
 size 3515