Run 2. Outer Step 6. Inner Step 569.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5337570,
-    5337574,
-    5337578,
-    5337582,
-    5337587
+    5337616,
+    5337620,
+    5337625,
+    5337629,
+    5337633
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 563,
+  "inner_step": 569,
   "inner_steps": 0,
   "last_allreduce_block": 5330632,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5d86b3ad1939838c2a4d3e27f3a6f8a1d6bfa2cc61b4a03c31054a27aa2858e
+oid sha256:04bc117d3f31a5167104950381b047187a1c33be041359957717a0e265308570
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31e23cf785b908ad1fa2b3823c516dcd24046ca9ff44c2be32467438e0b2b02
+oid sha256:de52de55a1b1db4900e4f07032cce35700147e2c4183fef23f29d48923c56432
 size 4040701744