Run 4. Outer Step 10. Inner Step 90.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506169,
-    5506173,
-    5506177,
-    5506181,
-    5506185,
-    5506189
+    5506193,
+    5506197,
+    5506200,
+    5506203,
+    5506207,
+    5506211
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 89,
+  "inner_step": 90,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ce2fc21c6c95652b3c9ea1dcb11e447365b144354581e139e1a4b2a1157678
+oid sha256:aff6df8ca5b0d0b0d4d575426a37bff97f37a0a85f9fe03417f297e85608b1d2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97a9248ee0f346af31ba676db5f95c7a66eb1561e5414143ccccbfc33e2a791
+oid sha256:f89587016860e5c4243d6db90acebb6cc1d94052c02f444beaa9ae4537b09b34
 size 4040701744