Run 4. Outer Step 52. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575884,
-    5575885,
-    5575887,
-    5575890,
-    5575893
+    5575896,
+    5575898,
+    5575901,
+    5575903,
+    5575904
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d8aad104fff4a193d2711de6d6ad421be3d7f2ff4a473df9e76d2f4f461033
+oid sha256:bdd3b373264c2974801837bd2c39981507a08b4f14f874a249cb39cb78c51ed3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327100f1b4781a0985ca04b8de2df10e7b43b16d2be08ff8abb7b43185aac5e5
+oid sha256:65ad0183845456d8eff128639c4d8f951f877f14435fa66ebe6c0a5dedc8964f
 size 4040701744