Run 4. Outer Step 83. Inner Step 23.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5673583,
-    5673601
+    5673619,
+    5673639
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5672513,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a038c7badca78ddeb4006a9579b540e25cc402d1e9c3cbd41897d5863a607e
+oid sha256:5411b58cb86442a1f410d6239523c5137502d6d01a73ed80fec5cf2a6c242761
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068c334e9939ad734dfc5f4efc2f0bd4a42efef4c842a288988890f58062d13e
+oid sha256:99d589088ef040f29f34cdeb83032ecee2c634a7219a09409a29c1d113f6d33f
 size 4040701744