Run 4. Outer Step 61. Inner Step 15.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610226,
-    5610230,
-    5610233,
-    5610238,
-    5610243
+    5610248,
+    5610252,
+    5610256,
+    5610260,
+    5610264
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 15,
   "inner_steps": 0,
   "last_allreduce_block": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8363cede1f146742e7bb3cb6f4952dfcf81f714ae02d6a68611df6c36e2e810d
+oid sha256:a6caa8e314f7f0120dccd33b9238e0e240fa9fb4c62b6c67c9130231a3118d71
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418082369cd85c18e4ce1684865f0887e669689729f3b9a66742286233da0ae2
+oid sha256:03156e3444e023a2acc128105b0d5119ef3cb3e0a385193c76bbb78cec3d1231
 size 4040701744