Run 4. Outer Step 50. Inner Step 36.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572517,
-    5572521,
-    5572525,
-    5572529,
-    5572533,
-    5572537,
-    5572541
+    5572546,
+    5572550,
+    5572554,
+    5572558,
+    5572562,
+    5572566,
+    5572570
   ],
   "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": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b276d2a333976843d6306724e6241e9c1e28b4e51738bb5aefa5be22d634e296
+oid sha256:5a36102ca663a3726dacc9726a6ebeaaf0adda16c9b5fa08897b5a6cd67799a0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f09b7ea9de7faafd59d4fc50e25c8073caaa201de8ed38221bd72c26713c8308
+oid sha256:788ae0ff9bf8b9e5fd4f52eac2d0efae46330ecfed0b3341f3e5a7eee541634e
 size 4040701744