Run 4. Outer Step 32. Inner Step 37.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543778,
-    5543781,
-    5543784,
-    5543785,
-    5543788,
-    5543791,
-    5543793,
-    5543796
+    5543798,
+    5543801,
+    5543802,
+    5543805,
+    5543807
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0e5bada887eb7531de5bf2ba45b4f24c5654a40dc9842d6868e9d6b83f9ca9
+oid sha256:0a7d63eea24215951dc9b2dea96a9401ae22044a18488c48576f05c6b69ea901
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607583c3ea37cd95bee378f0a68c2d08de059f3b81b6220f047a8c2a98f33dbe
+oid sha256:d9d20e93eb872620363bb8ded31b344340fda32c882fa198998a55d5d7604164
 size 4040701744