Run 2. Outer Step 12. Inner Step 0.

config.json

@@ -267,21 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5363429,
-    5363433,
-    5363438,
-    5363442,
-    5363446,
-    5363453,
-    5363463
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 61,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5339896,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8912bb0a0d2e915be9fcfef851ec501faa331e778bc242eaa657d82a57f4cfaf
+oid sha256:188e4ad136b45eb0709fa33fc4ee63dacd56477bdc44897e405d4162e6113526
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec303bfb2232d96f367a1f36bfa80afe24b62fe548b0168635c024f5d2abbe4e
+oid sha256:6236f6e38d3737de9afec34cf36f286ec380e83c20e55fd9fd7238d7f0bbc4b5
 size 4040701744