Run 4. Outer Step 35. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548373,
-    5548376,
-    5548380,
-    5548384,
-    5548388
+    5548392,
+    5548396,
+    5548400,
+    5548404,
+    5548408
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b3dd99b6e7ce006e6fa800a6db1a9b5232c5f7432885d48ee72021a7257091
+oid sha256:9365eda4e33b23409eb7409a88a6d75bbabef3ab0bfe26620aea91b36ea24f25
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840d91c7f2c0dc7dd563a3f2cd8585e124afa87707f47134c98281f6630afe5a
+oid sha256:9ead27cec5a7156bd04be7a2d6684a3b6acab760fb0542955e74aa660193f86c
 size 4040701744