Run 4. Outer Step 53. Inner Step 36.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577379,
-    5577381,
-    5577384,
-    5577386,
-    5577387,
-    5577388,
-    5577390,
-    5577393
+    5577396,
+    5577399,
+    5577401,
+    5577403,
+    5577406
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3466f6f10849c98795d3a105805542b4c39ff642ab53a933bb79409a21753c87
+oid sha256:7cee83a282bd622eb936c3253eb288a411afd3548105a60b87ee09f183a21b77
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca582d8f57ee8e385942b2526cb5776291df24aecac298bc172a2698396d7cb
+oid sha256:96b52eb27c42a8034d3bf82bf0a2a46a8515717d8d4ba336d3747d16e740179b
 size 4040701744