Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
     "BertForQuestionAnswering"
   ],
@@ -8,14 +8,14 @@
   "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,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849a59f71e71db8f80bced81e7e1b2420aaadc750d756b68f2b886d061f98847
-size 435643185
+oid sha256:b22a8e9ba9515e56628d1abbf7ad18e5e0e7f718ccde7ff7d8d891459e8a626f
+size 1336512689

runs/Aug11_08-18-32_1be7fe59a580/1660206317.0508385/events.out.tfevents.1660206317.1be7fe59a580.402.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78d4e01b201d73cca4487ebb4af50ab09c9617e1f2ea55d4c012865811ffac7
+size 5450

runs/Aug11_08-18-32_1be7fe59a580/events.out.tfevents.1660206317.1be7fe59a580.402.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e611a1a92cf0d121bf383ba7dd51db2333aaffa154fb35d6a6d311e2c7fe021d
+size 3691

runs/Aug11_08-26-39_1be7fe59a580/1660206482.9024284/events.out.tfevents.1660206482.1be7fe59a580.532.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5be3df94b0e852a6483a74259389231a1108610979a1b837352d6542a40e02
+size 5450

runs/Aug11_08-26-39_1be7fe59a580/events.out.tfevents.1660206482.1be7fe59a580.532.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6cf9418c729edde01721a8e6a2049fd4f92720799836af486ccb72e3b0aa4f
+size 3847

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "OnlySecond",
     "stride": 128
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 256
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -3,7 +3,7 @@
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "bert-base-uncased",
+  "name_or_path": "bert-large-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b7488f97da025180e210796811ecec5ddd5c9b83ad319282b873324fa7ae54
+oid sha256:21f2d1af2b461509c59568493fa72effe9106b7a86dde014eea50f6167118b23
 size 3375