Run 4. Outer Step 22. Inner Step 9.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526942,
-    5526948,
-    5526955,
-    5526962,
-    5526969
+    5526976,
+    5526983,
+    5526990,
+    5526997,
+    5527003
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d2faeda977728e296bb19ace0bf9e0850a34290064356d1a49acf4719090da
+oid sha256:bc43867bb8ba0b7c91000dc48c18e0254dbed0483382b190fb46b1e202bdab4e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f7db66c959d3b17a9ae59d6f2096b022c179aee62c17cea74b8f33911599d2
+oid sha256:59f4dcb34fa0254e0cea20b47d485bd0d7de449104d2339de7f47b73e513dc73
 size 4040701744