Run 4. Outer Step 17. Inner Step 61.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520702,
-    5520706,
-    5520709,
-    5520713,
-    5520717,
-    5520720
+    5520725,
+    5520729,
+    5520732,
+    5520736,
+    5520739,
+    5520743
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 60,
+  "inner_step": 61,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27af767239f150c0c518e4599632e68388bbf643ccb7c77a83ceda5bddc2ef6
+oid sha256:9daa30c60eaac63a96cad2ecee77fc6f80d9e9e7148373e47e181cd6afa43331
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d9b97f881b8f3ed4fd1ecdb81f0a3f4d4caa3ed14878cc58efa4c10c405a61
+oid sha256:a8e28546303d92c95fc4a31ecf71b462fbcae445da8ef16a1131956faeebce0b
 size 4040701744