Run 4. Outer Step 55. Inner Step 84.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5583374,
-    5583379,
-    5583384,
-    5583389,
-    5583393
+    5583398,
+    5583403,
+    5583408,
+    5583413,
+    5583417
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 83,
+  "inner_step": 84,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bfaab0b6f20f4c7e4125d45e74406336acf620496b8c2784a7b1f1a82b55fb3
+oid sha256:3a9e7b8ed9affa96a07fa062b867473a08307520db257879ed8c421022cc36bb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73612897683148d9aa8ecaaf9e1a70466544f92760c133a0c1d5a3669f4c1cb7
+oid sha256:46a25ca8f6f6e666d9dd26bcb39de0dd33c7d4213c96400671c5103479475ce5
 size 4040701744