Run 4. Outer Step 29. Inner Step 34.

config.json

@@ -268,25 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539546,
-    5539548,
-    5539550,
-    5539551,
-    5539552,
-    5539552,
-    5539553,
-    5539555,
-    5539558,
-    5539560,
-    5539563,
-    5539565
+    5539568,
+    5539570,
+    5539573,
+    5539575,
+    5539577,
+    5539580,
+    5539581,
+    5539583,
+    5539586
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:367cdfcf631b8f72c4fea1086a8c5bd3e324cf8315baf278730cb4f711ba1941
+oid sha256:b1fe5178c52c0eb591bae89b44883b109174f20e222dd4c3b5111a08eac1b49e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55114384c559fc6f661a8ef0a6aaa19351d9bf7f8e68537fab883e38209e0d4
+oid sha256:59aeaae5a7debde6d77ee78febde1a0418583b45459c16cab685a275de428284
 size 4040701744