Run 3. Outer Step 11. Inner Step 209.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5443364,
-    5443368,
-    5443371,
-    5443375,
-    5443379
+    5443409,
+    5443417,
+    5443421,
+    5443425,
+    5443429
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 207,
+  "inner_step": 209,
   "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 sha256:374b1d8b2954e9e73011fba4d004018d69b268df5c1e9b9456ce39fc2bb3ddf9
+oid sha256:e09757d50f5d05e140111284ca3e4c93dc833fc95385b1762356e4253f8c880e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6b1ce1a8e1ad56690a522703c13907928715b1239b76e04f828980449c8a19
+oid sha256:17fd85bc1717627bf3d0a1d43ed469bb16a4cae7484e61573a266e0074c14a93
 size 4040701744