Run 4. Outer Step 58. Inner Step 27.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604477,
-    5604482,
-    5604488,
-    5604493,
-    5604498
+    5604503,
+    5604509,
+    5604513,
+    5604519,
+    5604524
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3710cb8336cb9cc857e21fa4794c2176ccb9ec8829e10cbcf0ea54cc3e57003b
+oid sha256:644c38a58b63919a1f3a7309381b6b9d87c5a8a451422b768ce476c826133b82
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee7a506aea30af28b982ce469e0e2ed7abfe286bf11a9522b3b58de246bd93d
+oid sha256:0239da8e941acd66f1f8b22f9931f29159e3f2e3463988aa51cfa21c0edee903
 size 4040701744