Run 4. Outer Step 60. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607896,
-    5607901,
-    5607905,
-    5607909,
-    5607913
+    5607918,
+    5607923,
+    5607927,
+    5607932,
+    5607937
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "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 sha256:6c8102fae83c0db8f18e04b022a71606d9d39bf58c91a2151f38048a9045ca0d
+oid sha256:ac27965877dd8503066d1c747bc2cf660d45c739583353d1eb7559db076847b7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50970b2872303d4f8b38f5916d0abf4813960a2c10c979ae78b9d0a88b225cbf
+oid sha256:b9b29dcc1435ff700868c95db5bb3dd157f9e8d9ac879d9e6c87e373e24c7d38
 size 4040701744