Run 4. Outer Step 18. Inner Step 6.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521133,
-    5521137,
-    5521140,
-    5521144,
-    5521148,
-    5521152
+    5521156,
+    5521160,
+    5521163,
+    5521168,
+    5521172,
+    5521173
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3dc6bf814c670f2a060bc1953b206646d4e705dcec7dad018c2da9461ecf5c9
+oid sha256:2c1b8fd8be5a2fcb9e5de6d7ad7be320b7c3ce5e1b753c12a2529a0120e7f19c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fb8ac36002667fefc63d797a1bff00383d836310b6d998581a1111050c1093
+oid sha256:cb379269423591fa4cd4d13fda0309eb1669ae50dbb2d39001e5d2e91e6ff68b
 size 4040701744