Run 4. Outer Step 15. Inner Step 66.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514972,
-    5514975,
-    5514979,
-    5514983,
-    5514987
+    5514992,
+    5514996,
+    5514999,
+    5515003,
+    5515007,
+    5515010
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f8383e88cf7d645f31fda7dfc8c20950b85aa4ff6584b66c57f15b3a10e7e2
+oid sha256:24e20779e7c453f30b1db8b691778475a57bf14f55b9f4d712bb51349412cf09
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ef71214b04e1675d4654620003ed8073d0473cd8889842b945cc741c92caff
+oid sha256:784cb74a0458b531c798d886db211384f5daf3525f9924d0988a934e890ebd89
 size 4040701744