Run 4. Outer Step 58. Inner Step 9.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603941,
-    5603946,
-    5603950,
-    5603954,
-    5603959
+    5603964,
+    5603969,
+    5603973,
+    5603977,
+    5603981
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae594a446b221f6744993dbf8d22a4b0769d6639971bd33efe3d6dcce160021c
+oid sha256:1396135e658e6894f0d23329226d60a15d3e06d283fc38d1da1f43746250dd4b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:689bfa3bffe32b8eb5ed53fa176ffc3269235bf96216b2bd2bb1036052f1b11f
+oid sha256:c64dfcf940f4ec2ed6466a45a5e9c6dbf63f18868251b3fa143477cb1f3eabfe
 size 4040701744