Run 4. Outer Step 4. Inner Step 14.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486801,
-    5486804,
-    5486806,
-    5486808,
-    5486810,
-    5486813,
-    5486815
+    5486818,
+    5486820,
+    5486822,
+    5486825,
+    5486828
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea81607516217cb333a35cb25381bd3bfdee4f2780bfb076710e8cab3dad2454
+oid sha256:9aeb671874322555d0def0d9ac252625afb9a85350f22e3ceaf705a7237cc1f6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659aa736aca64a64d453d46efc12a79143c92927be7ea8159fd2c397e0d359b0
+oid sha256:3ece41b932d00f85186f0eae8ce513a5aed28937808398294249d58363aad73c
 size 4040701744