Run 4. Outer Step 83. Inner Step 21.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5673522,
-    5673539
+    5673557,
+    5673574
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5672513,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95bc77e3b66e626ebb4d8dc56ad3e744a83a778356eb8d83667d32e1ce2c428e
+oid sha256:295525c16f56cc264cda3b69a31c7cfb5f2767f78593310ab6ffa1a4dd214648
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b8d7c2835051c25ff1d755891f668a0c3c7ff654cc1700532dfef89b827e42
+oid sha256:33dffe6bffccbe347d7fdc3ea97922c466fc26c1d9c13d2431417eb47bfc08d4
 size 4040701744