Run 4. Outer Step 50. Inner Step 188.

config.json

@@ -267,13 +267,16 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5626216,
+    5626246
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 185,
+  "inner_step": 188,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91682d62da1a3ef88024e7cf2ce21d79e28a61a4fe540226c712877bd9ffa9c8
+oid sha256:6565e91158d052d1d76370a1597722d8b3e379ee084680f37f17e53cc9eecc7b
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892e9331f725c35aa53aab2070fb62aaa905e899f8e875eb7287fecdc511a4ee
+oid sha256:6bbd9cb50ced91fe124a983234f192b9ac4737de93f267473b046c9458d2ed44
 size 4040701744