Run 4. Outer Step 50. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572193,
-    5572196,
-    5572201,
-    5572205,
-    5572209
+    5572214,
+    5572218,
+    5572222,
+    5572227,
+    5572231
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "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:fce6c9fb434c26a1d3030ee1814b39d70ce91054527719e12cfb81492f79e723
+oid sha256:bda345bae3f2d9a378b2a3e1a4d03ec326e302ab9b9c2e8733d22d80a046a5e5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be1779e74fb1156c2063316f5401a764480155c40e92fac08a374c4ccfaf6a9
+oid sha256:042690017967b4ae5ac5b9007d8ddd12d6d7fb3e065d4c89bd2c3c8bd3e45c0b
 size 4040701744