Run 4. Outer Step 43. Inner Step 63.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5562726,
-    5562732,
-    5562737,
-    5562742,
-    5562747,
-    5562751
+    5562756,
+    5562762,
+    5562767,
+    5562772,
+    5562776,
+    5562780
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7656139269bc0d412f2814bb9699df3d39c95ed5edfac8e5f01f6a2a7b0a16c
+oid sha256:0943cb2a73ebd74e31014d4e11a85e424a99da84548fa3752d4f0984ffb926f6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac982f304cb087db2520fb944123f268a8b76e5aee1fc25f03c4f9ab69655600
+oid sha256:24542018484532916c887df7060715163e771f140e67892368f88cc8ff70accb
 size 4040701744