Run 4. Outer Step 15. Inner Step 80.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515467,
-    5515471,
-    5515474,
-    5515478,
-    5515482,
-    5515485
+    5515489,
+    5515493,
+    5515496,
+    5515500,
+    5515503,
+    5515507
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df143bce3591f146ebb3e60eb3b339e1ab49d013fb74b45adf4a3ab211fab707
+oid sha256:44635c4a4b11ca3634714f69e6255429762a0ac26f1c6221331ee84274779236
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f24369e97e09e469da164a8dc2385de92870b0e3de74fe0d203161bd3ab169
+oid sha256:55c34aa93cfa3bc111927794feadf64d21c06cec030a7923bcad88aa5e192d24
 size 4040701744