Run 4. Outer Step 60. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607730,
-    5607735,
-    5607739,
-    5607743,
-    5607748
+    5607753,
+    5607758,
+    5607762,
+    5607767,
+    5607772
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "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 sha256:160abb0b3b33db322104f1137ce2a3fe540a0973f597452f025b415ff39a2d9c
+oid sha256:bf6fa7270758d07ef3eb28db0211a760488d7158dfe095a35bb9d6873a353dcf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d334e674611022cfb47f2ae424901139ad7e4660a23352868c477907209830d
+oid sha256:12dc22627bb50093985286f249a2a6bf83d58f6a5dfdcf8be87a0ba6d904bd73
 size 4040701744