Run 4. Outer Step 21. Inner Step 21.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526023,
-    5526024,
-    5526026,
-    5526029,
-    5526032,
-    5526034,
-    5526036,
-    5526038,
-    5526040,
-    5526042
+    5526046,
+    5526049,
+    5526050,
+    5526051,
+    5526053
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5525369,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f6b4112531234699c5688d8525452259fa16144fd7c2ec5bc0a24ded6e7fdd7
+oid sha256:0cfd68ea1dfe7d7092ff142b781d05d5468c88d5029c91b28947faf007ef52dd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b269e91839ebf7846aba478857d792d312fb4494e5e33239420cc28e992c57
+oid sha256:8044bce6e3859408fee18b9d7f02cb0c68b138b5f88288169833fa13da41e193
 size 4040701744