Run 4. Outer Step 58. Inner Step 37.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5605399,
-    5605403,
-    5605407,
-    5605410,
-    5605414,
-    5605418
+    5605422,
+    5605426,
+    5605430,
+    5605432,
+    5605438
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "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:c35efcc0f86f631b6382244d15d611fe6bb070c227bcd302e4172b1f87854bdb
+oid sha256:1de729f58999bf92385a792ba159e4d286946948cf31469300ac6381ef0c63e6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441a4204208baace4f1eaba98f8c425697c42f00e6e964f3788a735d2d97d71d
+oid sha256:1a4a86ea3692c0f5240aa4b1291172882130bd8d8de7815d3f588d45aa9ee22f
 size 4040701744