Run 4. Outer Step 54. Inner Step 91.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580322,
-    5580324,
-    5580327,
-    5580329,
-    5580332,
-    5580333,
-    5580336
+    5580338,
+    5580339,
+    5580343,
+    5580345,
+    5580346
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 90,
+  "inner_step": 91,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e5260f162e113f2214960fccc86890dba044a977c2b92adb35e7dd9e2a75294
+oid sha256:8fbe929dcdaf838c8b3cec4e16adc35ef7342aae9b7484431fb4567256621211
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf080353d90253ae93fa634167e13e2249855eaa41226a53eac3e50eec05b906
+oid sha256:dec4b9a24addce3550ddb5550e3513f9b26e3a237acd7a7d5e588afef3475954
 size 4040701744