Run 4. Outer Step 37. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550901,
-    5550905,
-    5550909,
-    5550914,
-    5550918
+    5550924,
+    5550929,
+    5550933,
+    5550937,
+    5550941
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f599e2c7c6ad314bba54a9bb538d792c9ab12073b156173663a0a33ee6160fd0
+oid sha256:ac39277720e2745fe23cd2011764f2db97c225c5a6a5a305953f4bd6a44b2376
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f02152d66c4ea6a79aa3a807e69e7bb05b4d0162862578335e440b1c706594
+oid sha256:10d52038635b996919b0d2b5fa546ff561f5a089c3af61bf3b811dd2e32a6f36
 size 4040701744