Run 4. Outer Step 47. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5568225,
-    5568229,
-    5568234,
-    5568238,
-    5568242
+    5568247,
+    5568251,
+    5568256,
+    5568260,
+    5568264
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5567600,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1222915e5e2cd4ca8d8ce685a45f9454dc645d6e89dc162bc03d231db5a96e4
+oid sha256:16d3b71084c2bd69bb287f1508d1faa16fef6cc2fb197be4a6229acaf868daba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30f3c1b7914d94a1fdf3dfb2e7c5f56c96f706f4516093e68c39cd6e6493f2e
+oid sha256:7935fe4995879ad60c082a4ec71ac93793d5a91ad8314a03dd2cc8e612acad54
 size 4040701744