Run 3. Outer Step 8. Inner Step 1.

config.json

@@ -268,15 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5395579,
-    5395584
+    5395625,
+    5395630,
+    5395634,
+    5395638,
+    5395643
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5392742,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2d34027febdf33dff39ff7c9f9f79c8ee8d062168946379817036cd64ad988
+oid sha256:389483d340bed2226208bf902aeab0054e7def702dc0e328d5018cc57366afe5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2a9d55aee651626cc05e59ecb42509a80e9ee2f1b8352bf866c94ead072ded
+oid sha256:2e688b68fcd1587bb95958dea11f8b434e79ca426cecc78f3100ebb69f23303f
 size 4040701744