Run 4. Outer Step 66. Inner Step 100.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621957,
-    5621961,
-    5621965,
-    5621969,
-    5621973
+    5621978,
+    5621982,
+    5621986,
+    5621990,
+    5621994
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 99,
+  "inner_step": 100,
   "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:c055244e1efba85adbd568e10772f4b5eccd6da806bbec30a22ee695b9b57661
+oid sha256:843547cf935d72139be946bfa04f4d2ab176fdc3ea9b5289fd7605b32446ebd9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f531a48886e3506a93a1d267cd0fe3fae42c51157b0b813bfb2e572e02c70d
+oid sha256:5312e03576728754baac14d767d09886dc2f8d0e8b076bef6976680e69ed739b
 size 4040701744