Training in progress, epoch 1

config.json

@@ -7,7 +7,7 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "hidden_size": 512,
   "id2label": {
     "0": "LABEL_0"
   },
@@ -19,8 +19,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "regression",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170608d69eabade44be932741e13053a78d5de1aabf6f2ce4dff43e81e005770
-size 22821036
+oid sha256:20e1f51ec82de1ff73d1103b43fafdb7d06ba7dde66dc3ede41e029f8cbe61af
+size 199128369