Run 4. Outer Step 64. Inner Step 168.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5615787,
-    5615791,
-    5615795,
-    5615799,
-    5615804
+    5615809,
+    5615813,
+    5615817,
+    5615821,
+    5615825
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 167,
+  "inner_step": 168,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3752525e2e64d10c401fb4e312efedf550c2e07a1952ec07bcb37b7f90c15357
+oid sha256:3c1de46c21aa71223854d00fcc35b585d1f982e83c40eec9693ee2d9848a2a15
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da3de1b427c8e7a4e538896c783eebf1bb270dd980dad6640ea7ec46c068f4e
+oid sha256:7e7118fb80884b1f27a242368a3bf7e685040f52d39bbc68900b037db380a2e9
 size 4040701744