Run 4. Outer Step 29. Inner Step 14.

config.json

@@ -268,26 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538960,
-    5538962,
-    5538964,
-    5538965,
-    5538965,
-    5538967,
-    5538969,
-    5538971,
-    5538973,
-    5538975,
-    5538977,
-    5538980,
-    5538982
+    5538985,
+    5538987,
+    5538990,
+    5538992,
+    5538996
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54fd6c75b3c7411caf5450ac17e47df2e7d1918fbf3e527377d2f751f9331aa7
+oid sha256:a90a2f2a4b73a8c1e0e159f847cbf9cad6cef5ff9c405b920e654dd56e4eebc8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21712450cae7e00e27a415d519fb83792b915ba84ef1bb0951fda918a4bc9ea
+oid sha256:e2d7212f9c868cad4302b97de842b459b8e2a489b8d4513c7fd3497706e91df8
 size 4040701744