Run 4. Outer Step 60. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607847,
-    5607852,
-    5607856,
-    5607862,
-    5607867
+    5607872,
+    5607877,
+    5607882,
+    5607887,
+    5607891
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6973d26498f5c8abbff9bc891f9ac87abdedada2e0b27a79be9262ae6b5bdd
+oid sha256:6c8102fae83c0db8f18e04b022a71606d9d39bf58c91a2151f38048a9045ca0d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32bd15078e008a7d46b07bd00e05633def7e0d7916fbfa1cfa097aca209edf55
+oid sha256:50970b2872303d4f8b38f5916d0abf4813960a2c10c979ae78b9d0a88b225cbf
 size 4040701744