Run 4. Outer Step 2. Inner Step 17.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480559,
-    5480562,
-    5480565,
-    5480566,
-    5480568
+    5480570,
+    5480572,
+    5480574,
+    5480576,
+    5480578,
+    5480580,
+    5480582,
+    5480584,
+    5480586,
+    5480589
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c62b3e7eba549e5f402854fc9f196f0aa6ab759b64ddc8a928b784cc39a89f
+oid sha256:39e10f643baf9c9d2efa7aaa5b60e7ef18c23a6aae4932623070dfd8a208999a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0c4554da331be6d62be40508f5a97b23399b72488cf4107eec80d96d9a06a8
+oid sha256:f81aeaa1fdf3e6dbb622921229396c54ebecd9bfb8b4cf541cbd15bf7065eaa7
 size 4040701744