Run 4. Outer Step 58. Inner Step 54.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604001,
-    5604006,
-    5604011,
-    5604015,
-    5604019
+    5604023,
+    5604028,
+    5604032,
+    5604037,
+    5604042,
+    5604046
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 53,
+  "inner_step": 54,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1bf673332eab8d32fc3de042305b119ff81f6a9c1d21d69c318f8a0b4503016
+oid sha256:ceed35703e662ab6aa49ffcfd4a295dd20353b87922b673d6faafd5540356311
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9cc3f2fb5d757ae97928273f89c6f64f7389c1d1a3800ca290eda7e09720563
+oid sha256:4c05d827bd0a24122087d917650a29c358555cbc22fd94c2fd691e717da90718
 size 4040701744