Training in progress, epoch 1

config.json

@@ -1,20 +1,21 @@
 {
-  "_name_or_path": "my_awesome_swag_model",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForMultipleChoice"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
+  "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 sha256:8e21b140487b13318610485b1a293edddecfe289fd4357d8aa987857dc1f37e6
-size 17548796
+oid sha256:6fd0c6f4dce71ce44836d6eb0a72a3c4eb222d3ee2cae9048479872350ec1992
+size 437955572

runs/Jan07_13-58-38_97a669587ffa/events.out.tfevents.1736258341.97a669587ffa.1316.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad6dc290b432543e0d4ab243f3afb2afa4e87966808e36ca9356052f75968bb2
-size 5698
+oid sha256:b3d4af742af5084ccffe18346ca990505f0cc2884683e1085f88641453326c1c
+size 6363

runs/Jan07_14-00-04_97a669587ffa/events.out.tfevents.1736258436.97a669587ffa.1316.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f1fca1867c2634eb06a2a02e5d664261620cd3e11acbf7bbf18dd0b6e2f074
+size 5381

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca238b3381eef7e337a1ec9ec4b5faae000056b57b7349e6c01f6efa61098987
+oid sha256:2ae47419ef1156529ee66ff5c1eff2af1a0ba41bd11a586d2c306dd0ba776b44
 size 5368