Run 3. Outer Step 6. Inner Step 248.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5392848,
-    5392853,
-    5392858,
-    5392862,
-    5392867
+    5392901,
+    5392905,
+    5392909,
+    5392913,
+    5392918
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 246,
+  "inner_step": 248,
   "inner_steps": 0,
   "last_allreduce_block": 5363566,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:468f345241ad00b5fed555eabfdc7e892ef1cdd98b48a645a00dade635c244b9
+oid sha256:47cc9c82471db08b85ffd093f71245c6ac62deb0ad4b2567d7754d1df38f6d57
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1044e93825a3973968f65f72dd322ceac2f29455e028de9989bf3c2b3763648a
+oid sha256:65166d056717069d90a630763ac597518264c5e4f362fcf07e34c04fff315458
 size 4040701744