Run 4. Outer Step 66. Inner Step 8.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651198,
-    5651227
+    5651256,
+    5651286
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cab5bd1ecac4bac39246bcd856ec4205dd09106d2eb6b83ea43ad1087f6dc76
+oid sha256:4132a1e2fea314a30db0ad5b16c9055fa0dd10312667c71eda1e6e0808e62ecb
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deaaeaf3a1eed7c727b67005bd1e81d9758ffdefdfdde90d7d41b40fb1fcfc70
+oid sha256:87015c1c7703e99270f02f3771a41b20b64c5935f2d03a6651be74bc1c27bdc7
 size 4040701744