Run 4. Outer Step 60. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607918,
-    5607923,
-    5607927,
-    5607932,
-    5607937
+    5607942,
+    5607947,
+    5607951,
+    5607955,
+    5607960
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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:ac27965877dd8503066d1c747bc2cf660d45c739583353d1eb7559db076847b7
+oid sha256:05bd305692bc305044449036f59fb94c0a54e7270a6681fe9c3c459dcbd884bc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b29dcc1435ff700868c95db5bb3dd157f9e8d9ac879d9e6c87e373e24c7d38
+oid sha256:f13b140d17801a830e8d0f6fe4b730113c43ca50810e9c089241a85bee36e1ed
 size 4040701744