Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-large-uncased",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForMultipleChoice"
   ],
@@ -8,14 +8,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "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,
   "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 sha256:981b1577495233e2c66d9e19649a2b7d202e9eddeaa8146216ea6e4dcf446c02
-size 1340618660
+oid sha256:e55df034c6729dbbf5c5584ccccb4927a3029d6c616932a6ae7ada61048428e3
+size 437955572

runs/Jan19_15-10-54_a26b9b1b7dc5/events.out.tfevents.1705677054.a26b9b1b7dc5.701.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6292a768eb00bc110a593aa47f5741f46c3507461166b9f141eec436f8ea77c4
+size 5156

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83b98f971e9f4683a8e6f4cf14eae266f94b987ebe6e05aaac87574f033145b
+oid sha256:ef82e74c760a68b6a7fbf06b8ffe316964f7bb156bae9e7af93a4077ea4b25a6
 size 4600