Run 4. Outer Step 28. Inner Step 34.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538080,
-    5538083,
-    5538085,
-    5538088,
-    5538090,
-    5538091,
-    5538092,
-    5538094,
-    5538095,
-    5538098,
-    5538100
+    5538103,
+    5538106,
+    5538108,
+    5538109,
+    5538112
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e21c52d2fcbd515c8fed0ab87770ed6ad3c909cecd3bcd4d2f5bddbb62149114
+oid sha256:2da154c342c1e723ff8270d6cf7ea014b10ee32d15295ed8c2b2dbc610d23f8f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18eb5ac38029ff895c2ec561eb020710d6b9f6507677a7c5612e3b28ae9d156d
+oid sha256:19a6054d464719290aec8fb94dbdc56632106ea1cdd6264f53f074f298b3e1ae
 size 4040701744