Run 4. Outer Step 65. Inner Step 35.

config.json

@@ -267,16 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5648912,
-    5648943
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5639485,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf605b2de36b9ae593adccebd21b934d93f7bd55038640bfdb519284f0244cc
+oid sha256:4ecbd5c2f321009c3e2db5e6d062769cd0a025151cc52cbcb48e7537a14f89f6
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b93e86cf0ca7f36760ff4c748ee0e4743ead164e8d636f931697a98d93b5a54
+oid sha256:e179beafdd20f7ed93612aac07ae989384523290ddcc247424ec592b9d5fe62b
 size 4040701744