Run 4. Outer Step 58. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603254,
-    5603259,
-    5603263,
-    5603267,
-    5603272
+    5603277,
+    5603281,
+    5603285,
+    5603289,
+    5603294
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "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:cde20a2fc99d15b3c00c89e59df2a1978ee2979fc6eaed6d0294676856618c8e
+oid sha256:979267a8ba5121d4f1ba18f44df0b87528d7ba866b288d03e321d095583b4ada
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7e98fc79e3fd1cfe3ff98efa923e0bf953cce947a13accb13ef886565afaf4
+oid sha256:18df5b046bf848d7a8b8c87be13f495e925536afb324480c7577d7a04490b94b
 size 4040701744