Run 4. Outer Step 26. Inner Step 38.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535797,
-    5535799,
-    5535801,
-    5535803,
-    5535805,
-    5535807,
-    5535810,
-    5535813,
-    5535816
+    5535818,
+    5535820,
+    5535822,
+    5535824,
+    5535826
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f155306a2f64e0cb15c3e2876b9221b656b130cab38702af85505ee33dd9e8e
+oid sha256:f23a584ec787d9f803079897e45d86d4a30a97d4a8fec7ac72ac2ed28ccbfaad
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc226d5900ecdeee9d4228a0c16b3d4fda5adce2d88f5f3deba82a22ab9bc7c
+oid sha256:812589a94e766d31f56388e8a413c16f8f129ed1c3b35ec36d0ac7400c106df5
 size 4040701744