hebEMO

config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "total_flos": 6997313242916978688,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

log_history.json

@@ -0,0 +1,30 @@
+[
+  {
+    "loss": 0.3389603042602539,
+    "learning_rate": 1e-05,
+    "epoch": 3.7037037037037037,
+    "total_flos": 612003370642200,
+    "step": 100
+  },
+  {
+    "loss": 0.036590042114257815,
+    "learning_rate": 2e-05,
+    "epoch": 7.407407407407407,
+    "total_flos": 1217799011071800,
+    "step": 200
+  },
+  {
+    "loss": 0.004135627746582032,
+    "learning_rate": 3e-05,
+    "epoch": 11.11111111111111,
+    "total_flos": 1823594651501400,
+    "step": 300
+  },
+  {
+    "loss": 0.012257537841796874,
+    "learning_rate": 4e-05,
+    "epoch": 14.814814814814815,
+    "total_flos": 2435598022143600,
+    "step": 400
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36cf1d1d96290db9d61fac6d75203260a2e6b35c87a807384a34227eb9422c8
+size 438024063

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea4e5aaa688f7298b0ac6647adf55267eb96c2cb9cfbeb00120a26bce235c61
+size 1775