Run 4. Outer Step 99. Inner Step 2.

config.json

@@ -267,13 +267,16 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5694320,
+    5694448
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5694192,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1caa0e9c243bde9426af994dfb40871bc44ce075dae6a976bf6c5a30f681f9
-size 2944
+oid sha256:4a5a4edf6069b0afc7e356a2ea6f521f44623a8557bdb8daeeea49d97d329285
+size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680342a859ed8575c08833f1fb3326f90bb3cc8ffa66f1a4fa28cc18410ca358
+oid sha256:f11d601c129cf469e14c97f529a70cbdb96bd6b37e4655b10bb06d4c24d33411
 size 4040701744