Run 4. Outer Step 43. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563194,
-    5563198,
-    5563203,
-    5563207,
-    5563211
+    5563216,
+    5563220,
+    5563224,
+    5563228,
+    5563233
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5560919,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a332a9590a74b276ed2fdf23f62f862d22a646532541e53dc7abef8675dfbc8
+oid sha256:fd7eaa29ec0d600e45d5f089130999368c762101f692150cbe79bdb7f9febdc2
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871558408b9bc8bf013ee40e34c0259a683ab2b91167bb97d8685f888c0827cd
+oid sha256:15276c3d74597e82bf95c42f2f21c52659677af3e05096cfa4a31c58bc6d5ca8
 size 4040701744