Training in progress, epoch 1

config.json

@@ -4,7 +4,7 @@
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.3,
-  "classifier_dropout": null,
+  "classifier_dropout": 0.3,
   "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.3,
@@ -24,8 +24,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 8,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07bb2057893d91e38ad0ee1d731b84b71e1fd697e6d36ded25dbc80dd2ae5d7d
-size 322311788
+oid sha256:f965014e8ee8d8544a52a378658d8cfbe3e8ab49dc8889c3748049b9c04b015a
+size 435725300

runs/Sep20_16-45-10_aef78e88129c/events.out.tfevents.1726850711.aef78e88129c.1485.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b7eeeb8c459edb26448d482fc5d56d2fe9bbf62f7cd04eb8605b4511250d21
+size 5794

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4b5847ac7bece19f5526dc8a5ff26b6b8b503136d6f976ad29cc712aaa7161
+oid sha256:3f981baaa25171cacb99e2b32f008348ded3fde2957fee4c9cad5f09228f78b6
 size 5176