Run 4. Outer Step 29. Inner Step 24.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539796,
-    5539798,
-    5539801,
-    5539804,
-    5539807,
-    5539809,
-    5539811
+    5539814,
+    5539815,
+    5539817,
+    5539819,
+    5539821
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9eb2fdeeb90bee9216102776da30481f9e7062b6896c2480265b2a432cd9b1
+oid sha256:dc559a59a03df694a4885539faeed5fda99e530252434b5286e0b7a0239f8496
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c9f8001f63d1016d2729b3bb1c3be7e01581f1a379038da70e4be24393aeed
+oid sha256:6982eb1ee41f4a776dc189770b140c13c794883ede7cbe37142eb1f47a56869c
 size 4040701744