Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,7 +8,7 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -32,7 +32,7 @@
     "19": "LABEL_19"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -58,8 +58,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0edb310c3c23ca93abb841f9d375885ba02b86b51e9a51aabac3350ced08326
-size 438014016
+oid sha256:fa5be1a7102cc203d18bbe581c9c99d2e835aaa7ac0c64745404d76339d8e4f7
+size 1340696568

runs/Jun12_09-52-56_6c02225e0b32/events.out.tfevents.1718185977.6c02225e0b32.1298.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35511e98f7bb15d6a551b62d8997b9cb6ee6fea4cb4f5ddf305559707e84258b
+size 6374

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f71f4a6b4412fe3ac9045b21329f1787642c35cd37c41fcee93737ddef7f615
+oid sha256:e888335bb3644e708bb176362fc978710ffa463558bc8da1bc5d40ca4876ec59
 size 5176