Run 4. Outer Step 58. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604997,
-    5605001,
-    5605005,
-    5605009,
-    5605013
+    5605018,
+    5605022,
+    5605025,
+    5605029,
+    5605033
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "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 sha256:15fff27a0b075668141c839801b641d5e5008c6051d7a817ac0dc5000d00ec99
+oid sha256:8e40e33ad5efe55d3b4cc8a23e8859e0a0ce64510fcbcd28e7f5affed8a011a4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13b96fe43ef765a1b0daa35c0d959ef1313f37b0c1597efc44a871d07191a840
+oid sha256:7237f522695c0730970583f0c6924179b05ee13973399a90448d529774ee6d46
 size 4040701744