Run 4. Outer Step 33. Inner Step 7.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544206,
-    5544209,
-    5544211,
-    5544213,
-    5544215,
-    5544217,
-    5544219
+    5544221,
+    5544224,
+    5544226,
+    5544228,
+    5544231
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a1b332d06c7a9a5c8879d080055d84cd7ead3f8c933f8d9b466154d542ee1a
+oid sha256:9fbf19696fbe26f26a34383322b0c57df973f8feaaa02db483af476b98bf6508
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c88633f6dac1dfc3e69a2953a3806258ac648cf55c2e1a113440fb36866bc0
+oid sha256:ca37259fee42103909224877cf7f026d8ab8b6081fe09facca73fb64c7b4b080
 size 4040701744