Run 4. Outer Step 54. Inner Step 81.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579979,
-    5579982,
-    5579984,
-    5579987,
-    5579989,
-    5579991,
-    5579993
+    5579996,
+    5579997,
+    5580000,
+    5580002,
+    5580004
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 80,
+  "inner_step": 81,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b922b30f1ce8902deff7ba35f64dfb9f87a4e5287212762f8b1fcc3d8a7a13bc
+oid sha256:ced31aec48c86390bcd130649f93c5c806ff046fcfc22153f0d449eed0a00f14
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732687d82619da5c004d0e74f72ac1430b2dd048790ef2933c29da460e946970
+oid sha256:6ce147b88d5f8f6f829269027cc8f46a6cd45f515b8dd6452d8f8fef4ea5ed2d
 size 4040701744