Run 4. Outer Step 95. Inner Step 18.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5689813,
-    5689831
+    5689849,
+    5689866
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5689165,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7033fc2ce0172acc279ab8165cbb2252b699ad4f2df9c49c8dd3a5d4f741f20
+oid sha256:d3038a0b7fb3f195f20a814cd2846b5fa55265bf034e10f6ce408bce3b38c0c7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21da1e2b870700497dc3d1b8745ed213b5ef88579baad383a1ef95333bb0c566
+oid sha256:7db6a7f423fef398cd0dfbcacd5f93e20a69d2d80d9311717e33a24d0782c7a4
 size 4040701744