Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
     "BertForMultipleChoice"
   ],
@@ -8,14 +8,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "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:ff4d150e50b63f8be4c72189eb697822727c6dd72e819cdb35ddc81f2aa357af
-size 437955572
+oid sha256:401e6a637e70ff24bcb43ef42162f5bb6a1630fb73d64e0138cc2261ee1ca733
+size 1340618660

runs/Jan18_15-04-39_f148f4e77b4e/events.out.tfevents.1705590280.f148f4e77b4e.253.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069c250907cb4ad0af9eb77d73c47ec4df2249033a3c2d475a4ed801169b10ae
+size 5158

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88976d04de9fcd6ce3ed0d1239ad57639d5187cdff3103879b418b92085b6b4
+oid sha256:4f81ffe620f02489d9e0aff228ae20f0dd62a87004cbfe8064efb1aa540e6c5b
 size 4600