Run 4. Outer Step 22. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526906,
-    5526913,
-    5526920,
-    5526927,
-    5526934
+    5526942,
+    5526948,
+    5526955,
+    5526962,
+    5526969
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "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:e0df0fa4cecfca265f96a442c7339e3371f37d0c37750a864420ba91f080d61b
+oid sha256:31d2faeda977728e296bb19ace0bf9e0850a34290064356d1a49acf4719090da
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e1b54607a3623cede09542c1dfdfb3aad5ff04b3bd7b41bc7989995c6b999e
+oid sha256:99f7db66c959d3b17a9ae59d6f2096b022c179aee62c17cea74b8f33911599d2
 size 4040701744