Run 4. Outer Step 10. Inner Step 99.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506420,
-    5506426,
-    5506430,
-    5506434,
-    5506438
+    5506442,
+    5506447,
+    5506450,
+    5506455,
+    5506460
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 98,
+  "inner_step": 99,
   "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 sha256:9d71ab56a0833d1882934b99163b333c2c45014394d0e24ad2e7b6bff43b28b3
+oid sha256:e12ece64ec69f48d69544a081b791b88d4f16f1f6140d67a3781cc96d8c2b6bd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a72dad1a2741bcd064bace33395f4c24a90b1840d77888f172c971922f9697
+oid sha256:16ea7655f3bcadfd5172e3c0cbc7a8a11a2c4185329f2388e682c7ec380e0da3
 size 4040701744