Run 3. Outer Step 11. Inner Step 207.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5443324,
-    5443328,
-    5443331,
-    5443335,
-    5443339
+    5443364,
+    5443368,
+    5443371,
+    5443375,
+    5443379
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 206,
+  "inner_step": 207,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1979d2d460c34448c2b32fd3c536a6515f26534490beb989bf868bdc5b48bb
+oid sha256:374b1d8b2954e9e73011fba4d004018d69b268df5c1e9b9456ce39fc2bb3ddf9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4375df710585f326f5673fe3ab792099a77bfdcb83cc169d76b89e7cd6b7e3ff
+oid sha256:ce6b1ce1a8e1ad56690a522703c13907928715b1239b76e04f828980449c8a19
 size 4040701744