Run 4. Outer Step 29. Inner Step 21.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539172,
-    5539174,
-    5539176,
-    5539178,
-    5539181,
-    5539183,
-    5539185,
-    5539188
+    5539191,
+    5539194,
+    5539195,
+    5539196,
+    5539198
   ],
   "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": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2988e1523487925f1eb85b7006051209056e8556c8dcc1ab4fa69bb597d5dd
+oid sha256:9166376cba1b0bd7c4b23f9611434edde88708732f816384ce56014a3f5b4442
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1971d99f964a7409a1566184008d2823a6e793d937abd7f33145e4d3b2938da6
+oid sha256:5a1d0bdaabd534ecbfe3c3a3d47c93e8b288373e5a77c6315656ec2c71c6ee6c
 size 4040701744