Run 4. Outer Step 60. Inner Step 19.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607753,
-    5607758,
-    5607762,
-    5607767,
-    5607772
+    5607778,
+    5607782,
+    5607786,
+    5607791,
+    5607796
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "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:bf6fa7270758d07ef3eb28db0211a760488d7158dfe095a35bb9d6873a353dcf
+oid sha256:416d2bcb6ff2e04c441cd23a6274ee137899d6f4b2da41c10d69fca2aae32e50
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12dc22627bb50093985286f249a2a6bf83d58f6a5dfdcf8be87a0ba6d904bd73
+oid sha256:eae099317c05498ab0880b982a9a71b74e93e9ce3bbb6177cc509bac93b637c2
 size 4040701744