Run 4. Outer Step 26. Inner Step 30.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535582,
-    5535585,
-    5535588,
-    5535591,
-    5535593,
-    5535595,
-    5535598,
-    5535601
+    5535604,
+    5535607,
+    5535609,
+    5535611,
+    5535612
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b44609ba2d53e0d3b5e289a5578f5deabdd1a69a610bd2ad915acac1a73b8d1
+oid sha256:49d955cbd83237de56ac1be32ca21e66875768ec9b980913c27cc5682b54a621
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64dc616e9ccf478e37cd8ec8f9dad13916f840d1c996e43eb626ccf8037e21e
+oid sha256:b9a73c7691592e5d41b3c7f9e18fc6453984c966b974ca711c7b4c1d8e7a07b7
 size 4040701744