Run 4. Outer Step 50. Inner Step 52.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5573223,
-    5573229,
-    5573234,
-    5573239,
-    5573245
+    5573250,
+    5573255,
+    5573259,
+    5573264,
+    5573268
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 51,
+  "inner_step": 52,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a73c22977b13eb8c64996204d1411881e2c37787eba0564ecff854d31669d8ff
+oid sha256:643de2e3c98d90ba579c2e5baf508cd0d1099f32b8d469c13a0b23cc3a13a119
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a202240532742b92bd1e9261f686518d6c269db2cf3beb36ad6134b290ae81b8
+oid sha256:e6d732b3c59e600b128dcb488f032bac839cc6f6a5947401da3587b3af63197b
 size 4040701744