Run 4. Outer Step 11. Inner Step 27.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507728,
-    5507732,
-    5507735,
-    5507739,
-    5507743,
-    5507746
+    5507750,
+    5507754,
+    5507758,
+    5507761,
+    5507765,
+    5507769
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc31e2e956541fe2934a90d182d96ec3d835918fd3f395c08f6cf7b4f8ab6bea
+oid sha256:79d8c381a77704396a93c4d9fada45fc6e031ad27a801244175f5c94df9189f4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054ea6199b08fd23407948183eb95129c4375c1c34cf7a6c46495b29e2cb0140
+oid sha256:c3fde278897112a0a5f89cdb498713f14dd8059f3ce804c9e6bd9d3d510ca5bc
 size 4040701744