Run 4. Outer Step 50. Inner Step 175.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5626256,
-    5626261,
-    5626265,
-    5626269,
-    5626274
+    5626279,
+    5626284,
+    5626289,
+    5626293,
+    5626297
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 174,
+  "inner_step": 175,
   "inner_steps": 0,
   "last_allreduce_block": 5570305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9afc727178a286f4a8925b98d0c3bebdce9f55f288b456123df41eacba08d8ec
+oid sha256:1226aebe218e35d31b1904872606c45fc171060ad78789ca85f6656c53349ca7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca30eecd0ecc9a5242d2c0a0972ec66eb3d8b1477172c7650ddbd0c9e8edf36b
+oid sha256:b248ce6659342f7cf0e7ed9f94142b91ae4b22f6ef4c465a885871fac88b1ea5
 size 4040701744