Run 4. Outer Step 35. Inner Step 42.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549519,
-    5549521,
-    5549522,
-    5549524,
-    5549525
+    5549527,
+    5549528,
+    5549531,
+    5549533,
+    5549536
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5548219,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d53917422c32d9a642d62f7e2d09b9ca730691fa1f0992347e9d2e92f36995
+oid sha256:424af2c5eab1c02f934ee0191fa7b7ff606b08357acb5abda2f9de93b6b0a44b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d93de01512db3379b91188e3bab3ce1b05f001cfc88b452f39c40de0a0d14e
+oid sha256:f41a31a29b525728767d960b6a8ce7ee1095d63d42fe567ba042bb063ac4fa9d
 size 4040701744