Run 4. Outer Step 24. Inner Step 56.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5533330,
-    5533332,
-    5533334,
-    5533337,
-    5533339
+    5533341,
+    5533343,
+    5533345,
+    5533347,
+    5533350,
+    5533352,
+    5533354,
+    5533356,
+    5533358,
+    5533361,
+    5533363
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "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:e184044a4def4bb87d735bc94a3fc548f2713a7c47a892fefcf51e06f3d5ad75
+oid sha256:a033268705bb9b56623dad25e2eab26093dc8f3f35b7c2a334a13053495d5b8c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9194cfe2ee5a5a4f600afb83f4d5dba5f86ba1fe82f5b17d6074a1ff5c8f98ae
+oid sha256:e3196975621caa59ff11b367202aa5a7bbbf0c445b1c51cd284911192e3b1737
 size 4040701744