Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "prajjwal1/bert-tiny",
+  "_name_or_path": "prajjwal1/bert-mini",
   "architectures": [
     "BertForMultipleChoice"
   ],
@@ -7,14 +7,14 @@
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "hidden_size": 256,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
+  "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
   "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 sha256:02aa13925692d00ddb55daf30303c3c99ca8b890f5e3492d1ff780346643ff07
-size 17548796
+oid sha256:cc5217045880c0248df03ea759b76bd182951053c91326baaf07dfd3f2b3f9ff
+size 44691580

runs/Jan07_17-47-08_97a669587ffa/events.out.tfevents.1736272029.97a669587ffa.1316.25

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e851237edd508bb81bb98ddeb0c09fb88bd4926247adc0269d72036b9260983
-size 6607
+oid sha256:bc2d4ef0ea03ad2ea6edeb77caad252ba936f6982fa65a3bf20e8f7fe36576b2
+size 7284

runs/Jan07_18-14-44_97a669587ffa/events.out.tfevents.1736273685.97a669587ffa.1316.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df775cc8d34c0fb74e66446aee55e108f64bef13aa60eadeffe534b7c30ab14
+size 5298

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:033640a880f168ce3d133c929cd580da93d6410354b777a0b3a6aaf10248429b
+oid sha256:0e7a81913a2688622b74e2bee78d0c566b3b6e69d6382d1b562fec23f4ba8e26
 size 5368