Run 4. Outer Step 8. Inner Step 0.

config.json

@@ -268,18 +268,16 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494299,
-    5494305,
-    5494311,
-    5494316,
-    5494322
+    5494327,
+    5494333,
+    5494338
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 0,
   "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:e9724433a2eccedc91f9cc66aadd10e1fba113de58cfbd9d3642f520f69c405c
+oid sha256:d0f2f8a50d32e95f6f6228ff3c60fa43ac99022f1f8cb8ffca27f0c8bad23cf6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7150f4bf3ecc0956292eeda30b9979ea4e64a9ae086f91556fd82c7857e1c2c4
+oid sha256:318105f8c1220a1c1850ab5d112c6b1b738e05b146b9d226e1244c253dc813f3
 size 4040701744