Run 4. Outer Step 54. Inner Step 86.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580134,
-    5580136,
-    5580139,
-    5580141,
-    5580143,
-    5580146,
-    5580148
+    5580151,
+    5580154,
+    5580156,
+    5580158,
+    5580160
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 85,
+  "inner_step": 86,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031fe4a9b3cb5afaae27215ae6359fa090f1a0ac774eb6d31e0c561e54cbd82a
+oid sha256:8367192f34e40b770aed4db4f9fff5963a52b923f76b24a4f37b2123dc605e62
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948bce86f27f34878ca91dd724e76e5db7020d74613e7d0373aa2fbf6366cacb
+oid sha256:a494b4a8561b034f549cbdc6ae135dd566e43fa5d6156a780d12bde1b72393be
 size 4040701744