Training in progress, epoch 1

config.json

@@ -1,22 +1,28 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "bert-large-cased",
   "architectures": [
     "BertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "directionality": "bidi",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a24f31dad6c50b793fa86773cc380943e107df1e9ba9304ea8d78a525df6551
-size 430908208
+oid sha256:cc4861bffff402dbf02c560a96fc6a4724052298260afa0b908247506ba89ffa
+size 1330173664

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 384,
+    "strategy": "OnlySecond",
+    "stride": 128
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 384
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a8cced9421f0f934cdbce9379a271b27345e12ae9d5531ca52de0a733b9199
+oid sha256:98e728b3e4aa8067f6e745b997ecf3bbc3ab68c6d66fd1aa66258da2586df6b6
 size 4600