Run 4. Outer Step 50. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571931,
-    5571935,
-    5571940,
-    5571944,
-    5571948
+    5571952,
+    5571957,
+    5571960,
+    5571964,
+    5571968
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938b8451b473d1224e6bc76200b3e5d65db60e826d71496028f67f9f1d37db23
+oid sha256:87bd8a34e783bfe841bc7162f93354e0abf398a343a4fe05fd3717ab6bbcf028
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afd012fb03e14e2745bb7f2502dfcaea4f5c52ec2cd879c4aaaec5b9ef6c4fd
+oid sha256:09130ce4858f4c906d413c5113c1f9a9eb5eb057b7e85c90b63675912f651163
 size 4040701744