Run 4. Outer Step 64. Inner Step 231.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617549,
-    5617553,
-    5617558,
-    5617562,
-    5617567
+    5617573,
+    5617578,
+    5617582,
+    5617587,
+    5617591
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 230,
+  "inner_step": 231,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea772dd9e3cd8bacaadb7aff3d022c2d9ee35671c07f50a8030a8545d1b5fba
+oid sha256:c0718c91c571e8a5b4d54b4325d694cfe6a65edd99e049d65fdfe8fbe70ebb91
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0663a9867031e66875a58662a25c588f272887065ee390a21b7dfabe477bc554
+oid sha256:696df330d11cc633adb7663b0163d6a8bf06ae529abdb7e68b3de875b84e4c1a
 size 4040701744