Run 4. Outer Step 24. Inner Step 55.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5533269,
-    5533271,
-    5533273,
-    5533276,
-    5533278,
-    5533280,
-    5533283,
-    5533285,
-    5533287
+    5533291,
+    5533293,
+    5533296,
+    5533298,
+    5533301
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 54,
+  "inner_step": 55,
   "inner_steps": 0,
   "last_allreduce_block": 5531651,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95860090f9a439df60d5abecfbbbf39d0f008e79dacfb93e86ce63109fe8674d
+oid sha256:fd5a99945dd1a4f755279fbb08eb99224bad2784841fa9ec7a8b291b84cea4ee
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c356498ce58afdbed5a8bc65cb6a4b7055224769f9cdcc44b71166def7a4d43
+oid sha256:486ddbaa1878505fc727f7823f7f862537bd71ad4c5b0e0c773bb6ed3f48b7fe
 size 4040701744