Run 4. Outer Step 23. Inner Step 20.

config.json

@@ -268,24 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531472,
-    5531474,
-    5531476,
-    5531478,
-    5531479,
-    5531481,
-    5531483,
-    5531485,
-    5531487,
-    5531490,
-    5531493
+    5531496,
+    5531498,
+    5531501,
+    5531503,
+    5531506,
+    5531509,
+    5531510,
+    5531512,
+    5531513,
+    5531515,
+    5531517
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "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 sha256:943509d92779c97495de9d6e1930d63038b696de80c1b546d93c2b524e2c5374
+oid sha256:ae0db4e44f7425193a4b40e3a0ed83c670ebb11ba86db36c23ad37dfe2d42ff2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754a7d54b261838ba69c878d6b88ef78404974f43453b4c6b51d4e0c3437541d
+oid sha256:5ba6095ff846f80cd15cd433eb3dca510319f6afc39c16434f7db14c5edcce1c
 size 4040701744