Run 4. Outer Step 52. Inner Step 23.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575705,
-    5575707,
-    5575709,
-    5575712,
-    5575715,
-    5575717,
-    5575720
+    5575724,
+    5575726,
+    5575729,
+    5575732,
+    5575734
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a01972363e45843d631930732494dae31eb192060431bb89f6f6d4b9c6353daf
+oid sha256:c15ff739764e42700b31d7fe22ad99aecdf3daf9d3ed98e0bfe6bc6428dec74b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acae8ac445602ad56f5eedec984c223456cbdbe4532a06b04883937f1bb51514
+oid sha256:33d880d2db5c363a599138a957ba57de4a5da2b6c83537b06fe83cb0de8a30e2
 size 4040701744