Run 4. Outer Step 18. Inner Step 38.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5522153,
-    5522156,
-    5522160,
-    5522164,
-    5522167,
-    5522171
+    5522176,
+    5522179,
+    5522183,
+    5522187,
+    5522190,
+    5522194
   ],
   "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": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d9c50cef80816adcc48526b125827c1e3f946560036b0d2e67b6230288b7b8
+oid sha256:5cf718ae9d658d079aa1bb59e93f3b78d5e425a3daef8aa1b78e1b128c3bed6f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d642d0cd6da03e52fc06170297fb3be26f3474fdd1a4a7bf5e1268050817a4
+oid sha256:e3d69fedb8fcdf47128304ec7e038fe89d83e09b1bca01bc3bb81d3e7f6fbcc1
 size 4040701744