Run 4. Outer Step 62. Inner Step 11.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611090,
-    5611094,
-    5611099,
-    5611103,
-    5611107
+    5611112,
+    5611116,
+    5611121,
+    5611125,
+    5611130
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e275e568a8c04f51a1a3be3215f9858eea172f4ad7d52fbb339648c5af23d0a5
+oid sha256:77a54a458a249be9025426680f8d66b9f21ba293c386d55d283a09b4abe0104b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18373939c888ffbe4b6ed78073ac0867db20a9adef9f94fa6190e4308f0a2ca
+oid sha256:1915d84a2442ece768c3e5a8a67a8f14954ea9bebf3d09008ebf77027f714f5a
 size 4040701744