Run 4. Outer Step 23. Inner Step 24.

config.json

@@ -268,24 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531603,
-    5531605,
-    5531607,
-    5531610,
-    5531612,
-    5531614,
-    5531616,
-    5531618,
-    5531619,
-    5531622,
-    5531624
+    5531626,
+    5531628,
+    5531631,
+    5531634,
+    5531636,
+    5531638,
+    5531641,
+    5531644,
+    5531646
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eac6c8b6482c08fd242459ca781b301ef13dd86e5fa226e361595ceed9f756a
+oid sha256:ba9871130c0e79ab0fa1c25989ea40fd90a454bca923e189e4dba633624c6f0b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e6f5190ef65fee17dc80f0cf64dee8fe5078461058c293d9c1814ef32fe2bcb
+oid sha256:b7e208dcce4daf3f4d943d8b3eac167c009ec823f1d3c3a6725914755e72ab98
 size 4040701744