Run 4. Outer Step 28. Inner Step 33.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538141,
-    5538144,
-    5538147,
-    5538149,
-    5538151,
-    5538152,
-    5538153,
-    5538155
+    5538158,
+    5538160,
+    5538163,
+    5538165,
+    5538166
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64400c2e59f3fbd704d1f5468dc87bce51935fb93da4c5b7977a168e6956fba4
+oid sha256:0b58867bb522071a3d871395172542ce2d7a936fdf5ffced145f7511a6f2c5fa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4eb28be8e456b3434c0833b37c1faf6699ec2b4240b464541a1f1fff7357c05
+oid sha256:755677d1d7951f42ccb8bfeda1c3d9d5a53aaf4571dbae130f1c9361c951c8bb
 size 4040701744