Training in progress, step 500

config.json

@@ -8,7 +8,7 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 504,
   "initializer_range": 0.02,
   "intermediate_size": 2048,
   "layer_norm_eps": 1e-12,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958659a448cc079d3ffb77c7b6ebb5e336f558d94f8fe9b6ea39096b37bfc565
-size 216142827
+oid sha256:e13df2b87014cab750d8ae361cffd3049adc1467b972ef3b9cc5717e0044ebe0
+size 211976875

runs/Mar24_00-53-37_b5dfe0604ac8/events.out.tfevents.1648083225.b5dfe0604ac8.71.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511309e533f48fac58048c165c29c2216b9933b11e88ed32ed8bbcba485fb149
-size 3452
+oid sha256:2930cf8f9ab5544ced25bb00492573c05c3f862eb980db3a2158655ce9c40957
+size 4548

runs/Mar24_00-59-30_b5dfe0604ac8/1648083577.500567/events.out.tfevents.1648083577.b5dfe0604ac8.71.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54fe9269135a5e3560242b79bd4f487729c0d89d1401fc8bdadbb9b56d36252e
+size 4758

runs/Mar24_00-59-30_b5dfe0604ac8/events.out.tfevents.1648083577.b5dfe0604ac8.71.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335fca8e6266e9fc290eac780a36357e29159f5d0e219840adf585ba7dc73905
+size 3452

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa0f7647208dc9c742ca905eab43e214c0af9982dafb1d2cb6160d355970035
+oid sha256:80f254b9c2e32940cbd5f8e21f402f0c3ce8d59030b55b1bb6497b74e6cb6785
 size 3055