Run 4. Outer Step 18. Inner Step 14.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521542,
-    5521546,
-    5521549,
-    5521553,
-    5521556,
-    5521560
+    5521564,
+    5521568,
+    5521572,
+    5521575,
+    5521579,
+    5521583
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098a3dbb3d367fdd4813320feb29cbee193d20d7af095ff6155be62851c87e6c
+oid sha256:167029f3993d57161ab5aea45a1505c2679f1cfc8a95d5b4f7cc09026a3e993f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac667a96365eec2f5571798d2cb36372b961ae8a118e83147b89b2d4798e6a65
+oid sha256:f9208dc3a939a22c889b17e5f810e13ec27cdd77ad0c6893e135a8df6fc077b1
 size 4040701744