Run 4. Outer Step 96. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5690799,
-    5690814
+    5690829,
+    5690847
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5690407,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a84c501e1d15ef03917660ac38b60eb49b13238a0b8d1c01510a94d79ba8c8
+oid sha256:16399572719900e045195c08b67257c6b06b252108978ca0924b99b321df0e9c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a699c975759ca0cb4ff313acc002638f4db1e5037abc11eddee87bf3285cc7f
+oid sha256:71b37bf1a558c81de83df4f7bca16941297eab73da1cb0d2562161bc43d8c559
 size 4040701744