Training in progress, epoch 1

config.json

@@ -6,7 +6,7 @@
   "attention_head_size": 64,
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.5,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 384,
   "initializer_range": 0.02,
   "intermediate_size": 1536,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f6025a426b66b74a8c0c69de1dfcbc3599dcc066e7f4ec976ad5ab36fd8cd7
+oid sha256:94b123835ecfc8562aafee8acf641a409218e566d6ccce35b0f15b9327f642c5
 size 282651377

runs/Aug16_21-29-38_9a61bcd0d823/1692221506.1402729/events.out.tfevents.1692221506.9a61bcd0d823.227.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60da6dd7b70e7dcc344160cb3a3945de975416d8752a1d8a64e7226f66e784ae
+size 5942

runs/Aug16_21-29-38_9a61bcd0d823/events.out.tfevents.1692221506.9a61bcd0d823.227.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d46f7074c4d1f4ca7fb37ed8e72eff76fa12bc10ed7b3b92dd962f9c148364
+size 4695

tokenizer.json

@@ -4,7 +4,7 @@
     "direction": "Right",
     "max_length": 256,
     "strategy": "OnlySecond",
-    "stride": 128
+    "stride": 64
   },
   "padding": {
     "strategy": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec869d162a93a270fc436cae4000c2f3449fad951bf654dce34c070efea4b6d5
+oid sha256:676d9bdc26e84f0fac95f3221aead72e39c4cdc2d9d6dbc08eaa4e139f712402
 size 3643