Run 2. Outer Step 6. Inner Step 632.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5337945,
-    5337949,
-    5337954,
-    5337958,
-    5337962
+    5337993,
+    5337996,
+    5338001,
+    5338006,
+    5338010
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 626,
+  "inner_step": 632,
   "inner_steps": 0,
   "last_allreduce_block": 5330632,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfab04e8b607ec31ee33c09825f21086ece5eeda873d30314567fbed40e62323
+oid sha256:3e090819de392f90fa134432ece89e3d5cb2f222dc8398d88311f038c8696c10
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31fe4fbaf996e508f9f5710cd4d8e4678cab251d027140c659925421d752008
+oid sha256:8ce32e1e5aa40a39a2586fbee2425397b556416a9caaf0f13ad88a1c111d5901
 size 4040701744