Run 4. Outer Step 90. Inner Step 10.

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": [
-    5682406,
-    5682439
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5676357,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a0009029c92f11ba462f070dd95990a4120f1f5468d9f0a68ac69582221938
+oid sha256:257f9de00d95527a1ff7384f5c299e7a76e7d14b8d81402ebdcae4d81ab66a83
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33f79f72d95d13ec32c71df16f6f23cfeb1f85572599e220bd7a0fa6ec6ebad
+oid sha256:328bfadabb9887c7be4134de1e82d76e0bdf368146f63059ee2844d836a884ca
 size 4040701744