Run 4. Outer Step 55. Inner Step 10.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5583339,
-    5583342,
-    5583345,
-    5583347,
-    5583350,
-    5583353
+    5583356,
+    5583359,
+    5583362,
+    5583365,
+    5583368,
+    5583371
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216e582ce5324f50d90824dd32497e0d0d5c98d5ba34bf4b31bf4033a2655874
+oid sha256:9f9873d8fda8f268becadd21aef707c3710711c2a20a3595aa1837b9a890ec7b
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac40dfb49be744f6a271c8d170cb221e47c45fc252614691955e226d39af35af
+oid sha256:323488896b598c7f711a2ab5fe06f591ae88abeea2fee85b00aee539ef9bbfb6
 size 4040701744