Training in progress, epoch 1

config.json

@@ -1,24 +1,26 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForMultipleChoice"
+    "BertForMultipleChoice"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47127aceb0ffd926319c12d174171daf5c7ca50355a15d6f73d3ffdfe238cc2a
-size 267829484
+oid sha256:b8eddc032f7b752b209876d9cdad131318c1d6802b01441e2205936e90a811f3
+size 437955572

runs/Nov30_19-04-44_9478c48dd5a1/events.out.tfevents.1701371085.9478c48dd5a1.40807.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b5a5401f5b93ff7bd112f91cd9e5c690aa94cc00a7c3a6a4e48ecd27ddaf4c
+size 5310

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ceb08f4330232b9cfd229800ef54158318b48890891155b96a4507fad8f1fab
+oid sha256:af26f7788eb90d4bdcef097100bfd096319958eb0fdf5f482186657314422f4a
 size 4664