Run 4. Outer Step 50. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572171,
-    5572175,
-    5572179,
-    5572184,
-    5572188
+    5572193,
+    5572196,
+    5572201,
+    5572205,
+    5572209
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c2c03494685413bcc9273b210e9d1b7662004fead2613b31b277ae4087a319
+oid sha256:fce6c9fb434c26a1d3030ee1814b39d70ce91054527719e12cfb81492f79e723
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0027b19315d95b06967d22d888958fb31055d9a285acb14fb54688928d6ed6b1
+oid sha256:0be1779e74fb1156c2063316f5401a764480155c40e92fac08a374c4ccfaf6a9
 size 4040701744