Run 4. Outer Step 62. Inner Step 5.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610690,
-    5610695,
-    5610700,
-    5610705,
-    5610709
+    5610714,
+    5610718,
+    5610723,
+    5610727,
+    5610731
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76296797438b074ed80c63fe771a53f53eea05e6106cfcab7b6a04271beb349
+oid sha256:1403cf22fdf83de7f23b8c6a09f5f08cc33bb3c5edf96dc67c2c99a815d25d13
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7dc261a0ad957baf0c0c8c8e0f2d69c67984db656446ba3e7a363d261b3caa
+oid sha256:f0eb77c0007d82fdf5a063b40313bfcded53c34a475d83a61ef5d8e74824f2db
 size 4040701744