Run 4. Outer Step 30. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541103,
-    5541107,
-    5541112,
-    5541116,
-    5541120
+    5541125,
+    5541129,
+    5541134,
+    5541138,
+    5541142
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c787c0a925398d9dd84001b3fe2244924ae600024516507948b942713ed574
+oid sha256:2e6bb86770bef0a587bb560d12e943aec597f7db3fa4053b0acc4bd3451afaba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7866dbbeea536f6af07a044afb45c0988e394d309724c6bbb404c7ab5550c4
+oid sha256:28355b706a43d733f1bf8f2f38ddc82c28bdfec77a79d20bc9e1d18d2bfacdc4
 size 4040701744