Run 4. Outer Step 4. Inner Step 18.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486915,
-    5486918,
-    5486922,
-    5486925,
-    5486929
+    5486932,
+    5486935,
+    5486938,
+    5486940,
+    5486943,
+    5486945,
+    5486948
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f0e68439e357e00f97898a7330bb8c889286eafc54686010db04e6286e54c1
+oid sha256:c479a54a6f685e62fc87fac36812f0c015c0541294d983f8dc11958bad41591e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240922bdbad38cca2c80f03ecbde87b32e03cc19cdd4516a390c216096508748
+oid sha256:66c079c25392898875c9454cc49c27eaa7445b8a78ce7f2d6f3763d22cd67b8b
 size 4040701744