Run 4. Outer Step 54. Inner Step 56.

config.json

@@ -267,13 +267,19 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5595734,
+    5595738,
+    5595742,
+    5595746,
+    5595750
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "inner_steps": 0,
   "last_allreduce_block": 5573605,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02af40f6739d78fec34a93c1ab7df0bfff8d3d9a9e0a7762198cff66ff495a97
+oid sha256:e3dfe7ba9fdae0cca27450c82f0a5c43412d633c68171790679834bd63ad8bb6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23430fc67282185c3cb9e6fedba074bf49dc98e1e131f673c8c76a84ca484464
+oid sha256:f16d7dbd362e39660cd6b3a9fb01c1de0345df8e72bbb8809110f3b63bc43282
 size 4040701744