Run 4. Outer Step 58. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604957,
-    5604961,
-    5604965,
-    5604969,
-    5604973
+    5604978,
+    5604981,
+    5604985,
+    5604989,
+    5604993
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:279eda1b6705f510ae6fbc3da44873dcdc76f4d119fc96ee94cf376c6ba17562
+oid sha256:5b61993fc9eeaca8640a73d1343057753cbdbcf9d64e7873703025f189f5b998
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39ba78e077fd311054a08163aa9bcb1485e35fadb66275d603838e7bb476489
+oid sha256:51ffd3ef618b00b7b1e15c338d04a9fdddd5fee1be85b19e5272a95074e5c1b5
 size 4040701744