Run 4. Outer Step 66. Inner Step 100.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621928,
-    5621932,
-    5621936,
-    5621940,
-    5621944
+    5621949,
+    5621953,
+    5621957,
+    5621961,
+    5621964
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 99,
+  "inner_step": 100,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87225caaffefe08929eb0c336aff9abef034b1a0efaf2142292e2318c2474e7b
+oid sha256:c7a91bd9336168a35038f50b8cc0ac78c9b70a7c1b8fb8ca351e6a27a59b2b15
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb0e042a14d48845b8b36a774bb18856df6261b429a330450016e16e7f082e9
+oid sha256:2b38d4877fa8cff857d9fee33a80f14d559150f5567b6272dd6cfe1e2c3e0994
 size 4040701744