Run 3. Outer Step 9. Inner Step 1009.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421363,
-    5421366,
-    5421370,
-    5421373,
-    5421376
+    5421403,
+    5421408,
+    5421412,
+    5421415,
+    5421418
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1007,
+  "inner_step": 1009,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d06cfea03d07d536e7a69c065b299c6e751da6883983846e205086f25587cc5
+oid sha256:56a5524cbdafffa97ca4c3b95fdceec59eb75e4d76ae0ef20b7e16a0063687f1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e825ab188800118ba70a8abf35dceb0540e4aa8f71de5fd949ee3f2a7149402
+oid sha256:a9118990e64441b49827f401e6a0bbdafda760eaca130f91043d6ee11e93bc9f
 size 4040701744