Run 4. Outer Step 10. Inner Step 89.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506147,
-    5506150,
-    5506154,
-    5506157,
-    5506161,
-    5506165
+    5506169,
+    5506173,
+    5506177,
+    5506181,
+    5506185,
+    5506189
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 88,
+  "inner_step": 89,
   "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 sha256:49259d3854b6e113d0120b135fc48afa333d4ad779e24b4dad786aa87bcb3cb2
+oid sha256:a5ce2fc21c6c95652b3c9ea1dcb11e447365b144354581e139e1a4b2a1157678
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857d60231575e605571e5683bb349ef9b85cc3dd78ef6669356908604970e62b
+oid sha256:c97a9248ee0f346af31ba676db5f95c7a66eb1561e5414143ccccbfc33e2a791
 size 4040701744