Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-large-uncased",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForQuestionAnswering"
   ],
@@ -8,14 +8,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "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:f58bbb9b074ba85653b023b59d0aae7d0287a0ea253661b5bcf63b6542acb34e
-size 1336512689
+oid sha256:b990a3b395596ac5e1486bb88e66396dd693daa3b7576918d8d4dba4d6bec061
+size 435643185

runs/Aug09_08-32-25_58e64a916bd5/1660034595.2884285/events.out.tfevents.1660034595.58e64a916bd5.366.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e18126f9f5e75b464097d15bedc159997ac83ab025cf2a8a0c6587d51c1d4c4
+size 5450

runs/Aug09_08-32-25_58e64a916bd5/events.out.tfevents.1660034595.58e64a916bd5.366.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b96e7de04cff59232204e32630967ed4ac1591683e5bed913036b09eb181fa
+size 3846

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 384,
+    "max_length": 512,
     "strategy": "OnlySecond",
     "stride": 128
   },
   "padding": {
     "strategy": {
-      "Fixed": 384
+      "Fixed": 512
     },
     "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-large-uncased",
+  "name_or_path": "bert-base-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:a3860ab3bc7df498a089f71d586c0895494f02e3b1d706482620c2971a8ab15e
+oid sha256:91b7488f97da025180e210796811ecec5ddd5c9b83ad319282b873324fa7ae54
 size 3375