Run 4. Outer Step 54. Inner Step 82.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580149,
-    5580150,
-    5580152,
-    5580154,
-    5580156,
-    5580158,
-    5580160,
-    5580163
+    5580166,
+    5580169,
+    5580172,
+    5580175,
+    5580177
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 81,
+  "inner_step": 82,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed41ff625f8d868325f0ef8a5909fa8b7980ee28c7b23fbe5e42c698de149dc
+oid sha256:eb5965a4f66723d2b4efeb00dae61ecf112d5a9e103f05830e394afeb2631b0f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997d3fc953f65c80e7046b67d5822cfa5204d61f8c91db2d001c7dce29cbba35
+oid sha256:02214d39e21d7e296027f8287855660142e0c63a66f786630cf619fc4ae51c61
 size 4040701744