Run 4. Outer Step 4. Inner Step 42.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487667,
-    5487670,
-    5487672,
-    5487675,
-    5487678,
-    5487680,
-    5487682
+    5487685,
+    5487688,
+    5487689,
+    5487691,
+    5487693
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e1318b247d5582c31ee704d906e80b0cc21ff1a2c53f491cd509e507292504
+oid sha256:629ffd073d4b30c5afd993370a8ae9a3ff7be7a04fe374e633a4a99f90c6875f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3616904041626119396468b011dae5124e54788d8a52a9c5b4734bbd1bddc313
+oid sha256:d9af3607a04e2f5987437173c60ba1d0e79b6130de4623b940475287a172f2e1
 size 4040701744