Run 4. Outer Step 64. Inner Step 259.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617654,
-    5617658,
-    5617662,
-    5617666,
-    5617670
+    5617674,
+    5617678,
+    5617683,
+    5617686,
+    5617692
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 258,
+  "inner_step": 259,
   "inner_steps": 0,
   "last_allreduce_block": 5613899,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3892e5fbcd778970714e48a1730e7fea1a7247e151ec5a9aad7a54d31d8c7e2
+oid sha256:3e34f82855c911f8d0542d4c44ea5f7d4fab86c2812af6e90dc7cc7322b326b5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37876b7702670085c6b5e48e766d110c31089137003055d1f8786856542054a2
+oid sha256:dc1b1d19e39249b4e4b3db59c8d11e4f24cabb73229c580990f9d3e35c4717d2
 size 4040701744