Run 4. Outer Step 7. Inner Step 58.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494441,
-    5494446,
-    5494451,
-    5494456,
-    5494461
+    5494467,
+    5494473,
+    5494478,
+    5494483,
+    5494488
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 58,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abf002d71d128bc5671ed7a5e8ee1a9278efd66fb54a06759999e86d1c8de147
+oid sha256:c61a33de6cb670715a7a2dfc2ae02e31985dc67163cf753dae5c548dd65b3601
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7150f4bf3ecc0956292eeda30b9979ea4e64a9ae086f91556fd82c7857e1c2c4
+oid sha256:420486d1370461531a854ac3a22899919d5a5c48f2a6bd4fd1ff184ac191f2f5
 size 4040701744