Run 4. Outer Step 58. Inner Step 22.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603049,
-    5603052,
-    5603054,
-    5603058,
-    5603061,
-    5603063
+    5603066,
+    5603068,
+    5603069,
+    5603072,
+    5603074
   ],
   "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": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7388bf4b21852af210b3d8807503eb81736d0f50a2a91fbb11bfb86287a647cb
+oid sha256:83a4def1b067ee4fa52c237d1de19da577581990f026f4225a1840a3dce8f4b1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce61124e72d80c6e2f3893690a470cef92f9569292c62a540d6cad6efd454c85
+oid sha256:81a41e7175de66759aa491bfb1cda1156521a7a272e4c600fc289c45161a67ee
 size 4040701744