Run 4. Outer Step 12. Inner Step 28.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5509111,
-    5509115,
-    5509118,
-    5509122,
-    5509126,
-    5509130,
-    5509133
+    5509138,
+    5509141,
+    5509145,
+    5509148,
+    5509152,
+    5509156,
+    5509159
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcbb2939d60cf2a9542a6d84a2561eeb2204a41659fcc063e9d4dc38a72f17a
+oid sha256:20063f36ef94c48aa56616478e4147a2bfd3d2c60cc0492a44166020b62194af
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1485c485c46dc6dc565f8b3a0136dc112db94911f3d3fdaecada4eb0fc1c6634
+oid sha256:e8bc580e8d4dcf2e28130323ce26062d2b3ebb6545aac44ab732cf081ee30edd
 size 4040701744