Run 4. Outer Step 10. Inner Step 100.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506442,
-    5506447,
-    5506450,
-    5506455,
-    5506460
+    5506464,
+    5506468,
+    5506472,
+    5506475,
+    5506479,
+    5506483
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 99,
+  "inner_step": 100,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e12ece64ec69f48d69544a081b791b88d4f16f1f6140d67a3781cc96d8c2b6bd
+oid sha256:f64232dac769f9257d2fcb393c4ea0e421e5573948c2f44b9a4ea5f3f278d426
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ea7655f3bcadfd5172e3c0cbc7a8a11a2c4185329f2388e682c7ec380e0da3
+oid sha256:bb634b6e4a1f37139c1243a39b8c882bb9f7b7d1f951d7a137ca74ef6f34a320
 size 4040701744