Run 4. Outer Step 58. Inner Step 23.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603076,
-    5603078,
-    5603080,
-    5603083,
-    5603086,
-    5603089,
-    5603091
+    5603094,
+    5603097,
+    5603099,
+    5603103,
+    5603106
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a4def1b067ee4fa52c237d1de19da577581990f026f4225a1840a3dce8f4b1
+oid sha256:b0879834ff86caa1524dc7dde7598185a7297156c346daab836c692f911abd7e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a41e7175de66759aa491bfb1cda1156521a7a272e4c600fc289c45161a67ee
+oid sha256:7c68a9cf98ef445440fe84c410500e54cc39da70fc94b2588f51bd19cc0a9aff
 size 4040701744