Run 4. Outer Step 18. Inner Step 28.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521905,
-    5521909,
-    5521912,
-    5521916,
-    5521919
+    5521924,
+    5521927,
+    5521931,
+    5521935,
+    5521939,
+    5521943
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a7d40422f8961e6e6a4169390ae5e3afd1be20d50195ae3474bd42bb901318
+oid sha256:3aec72ce93a166e7953b810901056b1d11106a0a4a069eb7d783d0b4b32cf58f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c1e99931249e48b327f59110d81d500795a67c92ba0d377aeeab4c83d05f51
+oid sha256:aa1188483c5d514ccec77a4c3d768227f022856ab5bec10af2b298a676095490
 size 4040701744