Run 4. Outer Step 58. Inner Step 53.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604018,
-    5604020,
-    5604023,
-    5604025,
-    5604028,
-    5604030,
-    5604032
+    5604034,
+    5604036,
+    5604038,
+    5604041,
+    5604044
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 52,
+  "inner_step": 53,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94483ab30ba55e4190c57f891218ecc9e17d42b6ca7bd1553496acefe8c3149
+oid sha256:8ee6016d68b36270abd32b2bc26824e2db711e1f6a7d52a2404f65571935c687
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34bde196e59f662081fe2af113bb090497e965efe9de0c4cc61245ad0b96a86d
+oid sha256:982349c3a67e7297b1f6d9900f9e0572e469bffc18103480ca5c4369eb3b6ea8
 size 4040701744