Run 4. Outer Step 4. Inner Step 33.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487387,
-    5487390,
-    5487392,
-    5487395,
-    5487397,
-    5487399,
-    5487402
+    5487406,
+    5487409,
+    5487412,
+    5487413,
+    5487416
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff104a0c2bfd535c453ec536b15a3c2f19801224b6e08eb53fdd5eced7dc9d44
+oid sha256:3ddcb9debf84bb45415e1a2132dc174f7c6085cd4a18ac05087af881e0a8a9ea
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca65c2a7aedbb46d107f1680b4eaa9becfec863e2ec3f90bc43ef632cf8c492d
+oid sha256:dfb908fda6bd0704abc29e030eea79ef524cf91db0946d14656af098ecb98ae3
 size 4040701744