Training in progress, step 500

config.json

@@ -8,7 +8,7 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "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:de7554a9dd5b7884c407735e14dbb8cb4aea88adc684d7c9e2b3a369d8798edf
-size 362596331
+oid sha256:1e6e125e4b3cb3cf812101de7afa549a98e484ec0abf8b1c1d733963a7467e32
+size 152549867

runs/Mar24_01-15-08_b5dfe0604ac8/events.out.tfevents.1648084515.b5dfe0604ac8.71.17

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab2fa39ef8721a4b49a5d956ada9313e71fc2b525ccdeb2f227f6a8fc9108d2
-size 3452
+oid sha256:eb428a3d08f9ffff44faecb8e069f878f29ce72906685523c5c41b9f4344d740
+size 4548

runs/Mar24_01-15-08_b5dfe0604ac8/events.out.tfevents.1648084887.b5dfe0604ac8.71.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d92f4c4492766cb11f5527e39e917cb7ad1774a4b63b76db298af125c42390
+size 311

runs/Mar24_01-42-20_b5dfe0604ac8/1648086147.219124/events.out.tfevents.1648086147.b5dfe0604ac8.71.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8e0e75a0acd67d3f675f6446cede71733a5de6b2a2ad67cacbae130b29f575
+size 4758

runs/Mar24_01-42-20_b5dfe0604ac8/events.out.tfevents.1648086147.b5dfe0604ac8.71.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129656ba12f57f1b5245d7569581f48615a09e1a9f7fff3348ea8df71a123976
+size 3452

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330a2d476b3d028e928c270d13777cd16140ebfcbb77a491a0fe2644df391cf1
+oid sha256:21110e4cb3dc57835b05ae0f78e18c8889f1a9879c4ccb5383837244dcb7052b
 size 3055