Run 3. Outer Step 6. Inner Step 0.

config.json

@@ -267,19 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5384644,
-    5384649,
-    5384654,
-    5384658,
-    5384662
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 175,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5363566,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fa37137b4f0761c949077236d77ace385dbf122263603317c34d35131962a8
+oid sha256:029e2d644af2c47895985901a4cc7819ae308cc89b315f386b77a5c712cc0bd6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b30a5f09745b422e528500ed1f13646449ed68dd77794c7124f4c494b539c1
+oid sha256:80cd7494d566bbb7bea8a954f7160e952ae5af218c9a6d91b2968d3a2183f9da
 size 4040701744