Run 4. Outer Step 58. Inner Step 17.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604868,
-    5604872,
-    5604875,
-    5604879,
-    5604883
+    5604888,
+    5604892,
+    5604896,
+    5604900,
+    5604904,
+    5604908
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "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:b04e17f5167456d045e4832979453f40f73bd684cb7b66e100eb407720eff7f7
+oid sha256:ec523f8a6b465ca130558fdfd7815f59704006cb1f6f911cec371dfe4285863b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6339755032ab114a25322a7682d2bcaf6a8f6079699f2da5992f2187e99142ae
+oid sha256:d1005fe2f5c5527156ba73d260ac303d1409511d78cbb003903d74787621cde2
 size 4040701744