Run 4. Outer Step 15. Inner Step 60.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514815,
-    5514819,
-    5514823,
-    5514826,
-    5514830,
-    5514833
+    5514838,
+    5514841,
+    5514845,
+    5514848,
+    5514852,
+    5514856
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 59,
+  "inner_step": 60,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91eb17868025bb401d291f04eb1e7c213dd2d247628197024168389ad5f540c
+oid sha256:85988f0a6ed828b8114ea0e1622ef4ac51893758a3c1b37f620ccb90774960ab
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252de070cf03cd2a16e75f8e77896ada26973215222c8f6463c4f4c29bd1650c
+oid sha256:b2ac813de63288c5e7518580e972b49a4ab6354ffba043403cd3751e41bc2ace
 size 4040701744