Run 4. Outer Step 29. Inner Step 32.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539512,
-    5539515,
-    5539518,
-    5539519,
-    5539522,
-    5539525,
-    5539527
+    5539530,
+    5539533,
+    5539536,
+    5539539,
+    5539542
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "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:f9a3425fabf00c60fd3d268e614cd4bd85f70d2ee3af0ca062c3626aa8873065
+oid sha256:c7a2d636987de08b5172577d74cc3d44346fee7abf174ba43e720b2d611ecea9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c6ec226a2b015208b9d71f750c404ce0eb9cf612ee9a1297eb5af5c610d9959
+oid sha256:e5cfac88b53fd3ea052602c450a90794e9f3abce475d510cd67dd9c43e929df4
 size 4040701744