Run 4. Outer Step 33. Inner Step 5.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544149,
-    5544151,
-    5544152,
-    5544154,
-    5544156,
-    5544159,
-    5544161,
-    5544163
+    5544165,
+    5544168,
+    5544170,
+    5544171,
+    5544175
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e94d23119ed07cc3a74277c161a6229c67f01a978a8f55b0b04c19d8cc21cb1
+oid sha256:83500fc1faa345eb951cc28505ed258241bba1ea77847adec71294a101b4bff5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e39639f86ec95f755aac53a29a00a5cc8c5000cd57e7ee1494c6dd46a3ca78
+oid sha256:550f99bea89194a823d380d871086d99810dd1b5d9ce80f89e2a288f677ff966
 size 4040701744