Run 4. Outer Step 26. Inner Step 38.

config.json

@@ -268,22 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535556,
-    5535559,
-    5535562,
-    5535564,
-    5535567,
-    5535569,
-    5535570,
-    5535572,
-    5535575
+    5535577,
+    5535579,
+    5535580,
+    5535582,
+    5535584,
+    5535585,
+    5535586,
+    5535588,
+    5535590,
+    5535592,
+    5535594,
+    5535596
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0ed60975297828ae28f9f88a9a8336d72a9cf44697c0a7aecbd0556e791a11
+oid sha256:4b27abfb844e1547653b276894e5f34608ff739772c8948c21e3006596475ec9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f181d63ea8e5527e626b750426753dcfad40bdc24518c0ca1113f81f0d20ce
+oid sha256:19d8268c54ec21819b72ea695e514774b8fd59963263fee517bcf2e1db3133c7
 size 4040701744