Run 4. Outer Step 24. Inner Step 58.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5533333,
-    5533336,
-    5533339,
-    5533341,
-    5533344
+    5533347,
+    5533350,
+    5533352,
+    5533354,
+    5533356,
+    5533358,
+    5533361,
+    5533364,
+    5533366,
+    5533367,
+    5533369
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 58,
   "inner_steps": 0,
   "last_allreduce_block": 5531651,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852de9891e3cd2d181f37068f89e776f461adcfc884c1e66487b42ab2c65d87f
+oid sha256:691e2ae300d9d5193ed2de4b163059c2581759eb50776104a724ff5c13cf92e9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5772852da247db95243bb48dc3a88633a9513a68fbf7ce06780b8a9cc85cf188
+oid sha256:2f02d740228fd28749edc998c77d1fcceb78910f08651bb19ca66ff3f660aa50
 size 4040701744