Run 4. Outer Step 62. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611265,
-    5611270,
-    5611274,
-    5611279,
-    5611284
+    5611289,
+    5611293,
+    5611298,
+    5611303,
+    5611307
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d36c2fff61e993b8b90c4eca3f97d20577f8ca8e77d53c6f6f739966592bb77
+oid sha256:4da07ae69d9195765bc5aef297b461e12f5606a12f838f0cc9c18d857d30bf56
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261a4928724154082d0a2a5e9a10751b3d5e736854e9d6ebfb014d8602df652a
+oid sha256:2d1192224237090873af78aa543922fd972cf4898a5c758da874c7b58a62f5ec
 size 4040701744