Run 4. Outer Step 62. Inner Step 25.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611412,
-    5611416,
-    5611419,
-    5611423,
-    5611426
+    5611431,
+    5611435,
+    5611438,
+    5611442,
+    5611446
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:558ceb21d85598b8133501fb34ab528f31b5b11f0c400c54d5798f591534668f
+oid sha256:af6ed91955a70d612be2fa51baac2212402503c96b122d082d1812373e27a8d0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b7ae50d68248af7e5f0c2abd09edb85d1be8c47272b7e2ff1f51902d4af5f2
+oid sha256:8aacfb51911fae75fc09eddd4d43a729979f8f345931c6d50e03b2b8f90a8c12
 size 4040701744