Run 4. Outer Step 98. Inner Step 12.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5693692,
-    5693722
+    5693754,
+    5693786
   ],
   "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": 5692898,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69ed62d2a734428ef59e151be17666dc46bff734a86057a25eabb975bf937fb
+oid sha256:3f4cbda41f987a85fe68e246d15130e2ddff24fab0598f32786379067800a9c0
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfc5102288d3029c82933b66c932bfb50a20323224b04ee6a7d4660d71e8368
+oid sha256:8d02ffe53331b1fde56077c1287a5e0f2408f67a45233bdd2d37caaa352f1977
 size 4040701744