Run 4. Outer Step 40. Inner Step 34.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556300,
-    5556304,
-    5556308,
-    5556312,
-    5556316
+    5556321,
+    5556325,
+    5556329,
+    5556334,
+    5556338
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbb6063631e912859e492223fd1eccde3c9783e6e7124867786c5e7a317f73b
+oid sha256:217e144eb6dc8602824b26a248f201fdfb03b81d16bb178276464037001db71e
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f017ce3f9a689afd8f668120ff453cda72357deae82d5d6345127655cb98ed18
+oid sha256:956a0b194395fc00640bad11854298da226ac147168c2810cc27d57af37a7ff6
 size 4040701744