Run 4. Outer Step 96. Inner Step 24.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5691204,
-    5691220
+    5691237,
+    5691255
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 24,
   "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:b08ff5962cf86f6786c9bdb605ab7cde6eb42f798e94b6df18d834a49d422fd1
+oid sha256:b434073c01f3f5f06e7f64a4e43d3cac803735aff2dab49ca17cd6c560825c60
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc1fb3bbcf525051ef4c91e4d9f809302110d6eb0ffc2fd9a6bd9efc6285371
+oid sha256:47fd890f7b56622b8fc3c86a88c733562df946f017fc1c26ec47f4f3380c7d36
 size 4040701744