Run 4. Outer Step 10. Inner Step 76.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5505827,
-    5505831,
-    5505835,
-    5505838,
-    5505842,
-    5505845
+    5505850,
+    5505854,
+    5505857,
+    5505861,
+    5505864,
+    5505868
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 75,
+  "inner_step": 76,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d07c754d1a433181620190f5514422a2a280c16fe69e92404adeb833d81866
+oid sha256:f695743258b0812b2a77f7c89ea12727b5ed5ef1ab2d9cc91350bb17d627859e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:217e17539b1a3bc91171c72b175def43c162af63527c041d4d8a7e9ee27bfbff
+oid sha256:7b36d1de22c46ea8029af2028a044c01660b5c47b0b5099280cfa3e98d77c002
 size 4040701744