Training in progress, step 500

config.json

@@ -6,14 +6,14 @@
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
   "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 256,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc0867dbb6147ad6f911ae80685d578354f5382e66947ce7da9d05b82897a4a
-size 346901984
+oid sha256:ab454f8eee40a5ddca284e3b62d021c9b0dda354eeda7b944326b001f5932a6d
+size 111143696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d908f697210cbe87433e72976dea5e00d7b0eaad203fff0939ca6b6247a45c7c
+oid sha256:492789fdfb36b623728d51e6a247169662c152b54f82f24a5ffd9c1498bb064a
 size 4728