Run 4. Outer Step 55. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5598785,
-    5598789,
-    5598793,
-    5598797,
-    5598801
+    5598838,
+    5598842,
+    5598846,
+    5598851,
+    5598855
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95f895d4f0730a305a5755090929801e4505d4a71d16855129a2a0cd8b7cb35
+oid sha256:7ec2762bb7644edaec9a08f509a1d692eda450bb414c9ef43e58d126fffc4299
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64dc4337a84fad704058d71cc2a5a9111211989461800f2af8df2f90ef14d830
+oid sha256:4eabdbc1e9ee4844629690e7ce05eb769a149e3c2f3ed6572f21b52e0f8cbf11
 size 4040701744