Training in progress, epoch 1

config.json

@@ -11,15 +11,15 @@
   "eos_token_id": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "is_decoder": false,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5b2b37a2ce22aeba3fb38229f42feed0c914686fe56027d3e36f75c1f0e417
-size 1302144896
+oid sha256:5e5ee130b4ab3cb69514444d313f0ee6fc1b3af971a4146413d04f30787bcbaa
+size 409100240