Run 4. Outer Step 57. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601095,
-    5601102,
-    5601109,
-    5601116,
-    5601123
+    5601131,
+    5601138,
+    5601144,
+    5601151,
+    5601158
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9990fdc3343dd121289b344975af6dc8f2d63bd0610dc9d2033e11d63d61c9b
+oid sha256:bda5b8d81a340df0aa71debf2f267079f8f1cd156cd5e843855847a76c3f6b29
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62e1463b9588c2bbc9e387c6f30449641bce03b052a76674448fb7fddafd509
+oid sha256:94bb9fbbc3019d85ac1174994ae958cc69953078ea49c2e0d5728b683ff99e3b
 size 4040701744