Run 4. Outer Step 66. Inner Step 96.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621805,
-    5621808,
-    5621812,
-    5621816,
-    5621820
+    5621825,
+    5621830,
+    5621833,
+    5621837,
+    5621840
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb02adfe6986862adb1ca0ae821a91130bb25f8e80a762c24253f1091fc4a633
+oid sha256:cb8e27aa256271315e2c5f0890d0d55e9d60253b21fc057f3be33db663d0d6a3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d91f941ca3859172bd7e95e27860bea11a89a7854435f09b36a99f3c91eb92
+oid sha256:7681e7d0374b038d619a17af5fdb982ea8b84031b06614a335b55f35ea087420
 size 4040701744