Run 4. Outer Step 24. Inner Step 6.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531779,
-    5531783,
-    5531788,
-    5531792,
-    5531796
+    5531801,
+    5531806,
+    5531810,
+    5531814,
+    5531818,
+    5531823
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5526620,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ddd340f541709955e6dae7d8fbfcd1b3cf2b7bbd4a958fc5f81c2e12c0bb1a
+oid sha256:2d62853c81f85c67f9dd0ebd2720261e1bb35c87328ea45053ce15db31ff7548
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584f32571bf1eac4c8a32c40bd54465dc21a108442bb3058f796243bba74c54e
+oid sha256:0f5647749a9f7dbe88a295121df8178711808d1ac900b76ed5f0bd7b381c7442
 size 4040701744