Run 4. Outer Step 55. Inner Step 6.

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": [
-    5633027,
-    5633057
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5632906,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12ef7832d38184310446c2b0a5dc6932e57cc7e52ab903e10c0fe4e64f2f92e7
+oid sha256:f19fdb89b869df984985860d061b40484efbe03b38a0f88739f053b08473776f
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75891c59b51a2ef86fb3d8fae433cea6c3b22db189ef20551c64fd6620f74b2a
+oid sha256:44160738d6dbe4fafb5ac51bad059db6988368635d800b14bc3324c3562e3cfd
 size 4040701744