Upload policy weights, train config and readme

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e462f8aa60e5c5ad14a4698ea925ef13c0a4795fb2bc325d3c0ce18b897fb535
+oid sha256:bf5dce45da482ee7903e2c904d46d82eea4cea7f6570e7d0002a38c3f84d81d7
 size 7473096344

train_config.json

@@ -155,7 +155,7 @@
     "seed": 1000,
     "num_workers": 4,
     "batch_size": 2,
-    "steps": 48000,
+    "steps": 96000,
     "eval_freq": 20000,
     "log_freq": 200,
     "save_checkpoint": true,