Run 4. Outer Step 24. Inner Step 59.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5533371,
-    5533374,
-    5533377,
-    5533379,
-    5533382
+    5533384,
+    5533386,
+    5533389,
+    5533391,
+    5533394,
+    5533396,
+    5533397,
+    5533399,
+    5533401,
+    5533403,
+    5533405
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 58,
+  "inner_step": 59,
   "inner_steps": 0,
   "last_allreduce_block": 5531651,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:939c73e0ecac28cf41bc1da70969abb099fc44cb2567afc70b7e76638577f004
+oid sha256:582ced5b5ad42fbd93212bd60b4e6b7cd9723b8b948442d7ad7f891c3c6ce023
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d460ea57bd38e1ae446931b9e11f6db02677818e4fb4a162262a0eb9bb8e06a
+oid sha256:50357f474eb1716cec7b477052b69b7acb156969d1b155ee7a37df364f9e01f5
 size 4040701744