Run 4. Outer Step 63. Inner Step 59.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5613868,
-    5613868,
-    5613869,
-    5613869,
-    5613870
+    5613870,
+    5613870,
+    5613871,
+    5613871,
+    5613872
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 58,
+  "inner_step": 59,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098789380db87d29a0414dbc6fa20dfb2664ae72fdbf094ff1310b1295ea8b74
+oid sha256:a93e99cf386b975f6368a5049818a3f32ca5abcabc44540078a3a3e06adf454c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a27e6b3dd4e7139159e1d398a498d3c02e2de72a25e4838066884d98f111a915
+oid sha256:25d07cdb59521877964f4cc698624b9540c75fcb3d198916b37a21d1195b808f
 size 4040701744