Run 3. Outer Step 6. Inner Step 233.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5388851,
-    5388854,
-    5388858,
-    5388861,
-    5388865
+    5388894,
+    5388898,
+    5388901,
+    5388904,
+    5388908
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 230,
+  "inner_step": 233,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7677e25fcd9b00bf45c71adcacbcffb39aa5e5df76c86a4722058437e547cabe
+oid sha256:82eb1b3e020e06ae246c256bf7abf9a2a25b3d4a7d478d603df6f3aeee17c13c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e80c844c329d876d8962cce53dcaf6ab22d4241cadc13678be46cf4c545e3070
+oid sha256:81996053b973cf3e05c2e3fa36e3b8a105f9845cc5c632e0aa6f48145b2ba890
 size 4040701744