large,oscar, comments v0.1

README.md

@@ -1,7 +1,14 @@
 # THIS IS BETA REPO
 We will release a better one soon:)
 
+
 <br><br>
+## train details:
+**token**: large vocab(52K) <br>
+**lm dataset**: OSCAR<br>
+**sentiment dataset**: comments on news
+
+
 
 ## HeBERT: Pre-trained BERT for Polarity Analysis and Emotion Recognition
 HeBERT is a Hebrew pretrained language model. It is based on Google's BERT architecture and it is BERT-Base config [(Devlin et al. 2018)](https://arxiv.org/abs/1810.04805). <br>

config.json

@@ -7,15 +7,25 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 514,
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "total_flos": 3118796722622472192,
+  "total_flos": 5334805906902687744,
   "type_vocab_size": 1,
   "vocab_size": 52000
 }

log_history.json

@@ -1 +0,0 @@
-[]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c18b6c74323cc1d85483e93c48b66f6ad0a456bfc427e0ce74a1e667fe2825
-size 333858111
+oid sha256:0e60bc1ed17e031223198e8d54cd776975b2ab447d91281ab9419f25feb4ddc7
+size 333861183

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f50e8cde1db05799ace5177491a0b663684c58e0226b05be15789d636ce053e
+oid sha256:ab1d77889f7695c8eb2f2631c8e21f7f2461cb9d9df43a8f982bb3674bfa2fee
 size 1839