Run 4. Outer Step 30. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541059,
-    5541063,
-    5541067,
-    5541071,
-    5541076
+    5541080,
+    5541085,
+    5541089,
+    5541093,
+    5541098
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "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 sha256:7250fd4421f679235611810dbbae589f494a1cb31dd562075368416418043724
+oid sha256:76d77638bce807d7dfe66366a74aa0db16914b768997adb610ecc010eb986a0f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65af1f9d2d227ab99671842c45f2468e4cdba2691c2ff734fd1d079ade10c1a0
+oid sha256:c2b338521f3df7179e6463549f424527cc9b3045e1909da611f9ecfd34cc7183
 size 4040701744