Run 4. Outer Step 103. Inner Step 12.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5699856,
-    5699885
+    5699915,
+    5699945
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5696880,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf001141a6a618b4ffcbd7d8fd4d1b1bd69f0bb53f990b463a887a0160d7b06
+oid sha256:1b329dde15378c2fd4ecf1456b8726769f51e069ff533bd2dc5d36a7931da666
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45fd30c6ad9be61edbe9434e191a39799899251bc9635d04c3d8c18fbcef0fa7
+oid sha256:6f06f675743c67149c9125cbd83f3edb81b850f664eda2b5c5f1b9a66fbab362
 size 4040701744