Run 4. Outer Step 33. Inner Step 25.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544773,
-    5544775,
-    5544777,
-    5544779,
-    5544783,
-    5544786,
-    5544788
+    5544791,
+    5544794,
+    5544796,
+    5544798,
+    5544801
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "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 sha256:671e83bd074098a7ddbf8184bb32edab16ca8931ecfb71f8f77dae6610ca1eb3
+oid sha256:1bf4d31049492ff61a79bc3c418c91f090d793906b5e2504001f1f29bb122a17
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57beebdb37ade10239af97bee4433d0b75062c73c806614efbd233095c73ad01
+oid sha256:401e1a0e01d17a2b564feecd285aaa0c3da794c63927c27394ea4a72b54a5415
 size 4040701744