Run 4. Outer Step 32. Inner Step 32.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543719,
-    5543721,
-    5543723,
-    5543725,
-    5543728
+    5543732,
+    5543735,
+    5543738,
+    5543741,
+    5543744
   ],
   "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": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae0707c09e21101678d883094ade481a4c4ba24cb0c6f5665ada9ebb7583bf3
+oid sha256:4d7dbf924d68b1c2f6b9743e3281099e22d6a30525f413d9b4037533c02d2421
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a390a12c24225023fe7ff19e6510cac164e7520607d5deb8ae91c46df81d21a
+oid sha256:4b43db5452c402ce1f238e05db718e097b00cb4d09bd422471090d38a59e4745
 size 4040701744