Run 4. Outer Step 7. Inner Step 66.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494708,
-    5494713,
-    5494718,
-    5494723,
-    5494729
+    5494734,
+    5494740,
+    5494744,
+    5494750,
+    5494754
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "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:c30ca41aa14d31ae56f6096e6c37c116753734e292d8381f4c64e0be8f0ef88f
+oid sha256:8343231c6d2e6e32c1de8b3b052f00a29c46335ad843c5343ca713f327873b6b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72c7196e41f3251d16ae2b40716510f3ad95f5564ef17f87707e6c81b0ab050
+oid sha256:701f4af969ebac49e17edf5da10fa5084440a1cd8643607e60fc423fd8c24feb
 size 4040701744