Run 4. Outer Step 75. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5663109,
-    5663124
+    5663142,
+    5663160
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5662361,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1693c50da50890e96b4ff80a4c1db288af5ef4c8e27d6bfa9bca34f3e3452da
+oid sha256:898ca2399a303b39386625dd555d262e01cba46d18796af7b703d999b095421e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1b178e0bfb9e59181f005ae3c0cb99287e9e87e26938a15429dd0a657c624e
+oid sha256:fdd4f138d81839c807a5b08093f708a379fac9ddf0894f9eb4769efc830a1c2b
 size 4040701744