Run 4. Outer Step 54. Inner Step 129.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597746,
-    5597751,
-    5597755,
-    5597759,
-    5597763
+    5597768,
+    5597772,
+    5597776,
+    5597781,
+    5597785
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 128,
+  "inner_step": 129,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d335971ab5cbaaaa37c08e920bfa236039ba97714031dccd1cadd844f0ad97
+oid sha256:adeb257f0f1833497697f4454bb35e3c230a63406fa970aa4ef7190f561e9296
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0751eb6b78aa4bd981f83e99e0619eae99b1f65f5a9d1c2481c4860d2c22eb9b
+oid sha256:8cea6181b303b38067b15e85de1cb25d40cd11201235a71b874ccaf019280f98
 size 4040701744