Run 4. Outer Step 35. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548649,
-    5548653,
-    5548658,
-    5548662,
-    5548666
+    5548670,
+    5548675,
+    5548679,
+    5548683,
+    5548688
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "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 sha256:384188b3f5186a223d5b4af3f95184296843dc773a07c57937781d1882e44245
+oid sha256:0983b0fc58d8ead89281cb8cbc13fe3eb168da5fa1d1d73f84d5c3ad5062fb13
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67aae76c4cd38ea09f30d025a69bac8f78dd43ec9d37671e31176758fc3828c6
+oid sha256:8cb991388835b6ebb7aacec93aa82847c426cb3cc75cdb4a75825dfb67f1be64
 size 4040701744