Run 4. Outer Step 26. Inner Step 32.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535636,
-    5535639,
-    5535640,
-    5535641,
-    5535644,
-    5535647,
-    5535649,
-    5535651,
-    5535653,
-    5535655
+    5535657,
+    5535659,
+    5535661,
+    5535663,
+    5535665
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e1120678817feaa0725585f5c277bf0b27aab041824510cec236f90184a7a85
+oid sha256:e0fbd18b82f514d06291926ce099b09da33ab9840f8f1045a8d9e3411c028eb0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18589586937081d6363e49f4714dd3b89e249bc533ee0eaebffdb0dffef69d3d
+oid sha256:396bb0ba7a54030f3f28de9de2378aa645d47a1ef0b65e75d356a781969d9598
 size 4040701744