Run 4. Outer Step 87. Inner Step 12.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5677848,
-    5677873
+    5677901,
+    5677926
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5673692,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd3b065565335888f869e218f1ec08c8575a4887d1427c312b4f73fa0af995d
+oid sha256:a2b386a6355fddf9027767239e6b04146631372e67907f7bd1435cf822bf3bfe
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1c12ef551fd6be1d51514b3ad3af04821e7d0521b7c216167a0010da6c2623
+oid sha256:2716c9347d7284e1f5c57b74de71b899df49fad4dbf4ea43efff9f947441eb7e
 size 4040701744