Run 4. Outer Step 62. Inner Step 26.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611456,
-    5611461,
-    5611465,
-    5611469,
-    5611472
+    5611478,
+    5611482,
+    5611486,
+    5611490,
+    5611494,
+    5611498
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "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 sha256:993d16f1824188a21eb0f01246a89f2c4a6051a9615900fd75c3f9c482b32a11
+oid sha256:8c520a421ec7133fc459bfcf2a5a245fc4c13d415c18283948d4d4dce65d26c5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e86f3e5f59105276c37703666ef26c8db07414bc69948adbb658caa67542ad9
+oid sha256:b858beb70613b905a046f9a4a95b5b578adeb00d92028d0b097f5118c581b760
 size 4040701744