Run 4. Outer Step 11. Inner Step 38.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507988,
-    5507992,
-    5507995,
-    5507999,
-    5508002,
-    5508006
+    5508010,
+    5508013,
+    5508017,
+    5508021,
+    5508024,
+    5508028
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300309ae55be49aa401c584756fb59ae630eec0607d052e794dd3ca8724abe27
+oid sha256:58c047dffad6403d797a6b1df03253e70dae22f2cd41a940e9b6e9708b991aab
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801dfee8a062d071e023202449634f10f14d01d12abcd1e340f29946bce23034
+oid sha256:3dda63741b092c457b0e307de34dcf22c31595615f6b3f1921dc689c6cbc86a0
 size 4040701744