Run 4. Outer Step 62. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611070,
-    5611075,
-    5611080,
-    5611085,
-    5611089
+    5611095,
+    5611099,
+    5611104,
+    5611108,
+    5611113
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e4555ff847f305a15b30e3084d100d53f15b9dc2136d8c6380ff09bbcb30ac
+oid sha256:64dbf01f65622ab0e592ebaf9ea1e6521e2c98368cd63f2aba6daf1658a687cd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d153a1601c933ca750221564f981b82f9e34ff5a2fba277be0b0399732bef3
+oid sha256:19b47d9e1c0a2bb4ffb9bfbab8652f24153ff0011225ffe7d8c268fc5533c4ed
 size 4040701744