Run 4. Outer Step 58. Inner Step 56.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604098,
-    5604100,
-    5604103,
-    5604105,
-    5604107,
-    5604109,
-    5604111,
-    5604113
+    5604116,
+    5604118,
+    5604120,
+    5604122,
+    5604125
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "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 sha256:305438af66e5029a85e192411335245fd3927fe1cdd7a29cdcef6b8eb7c93fa0
+oid sha256:0a3e505b21c8ec4f575c1e6c5d9a3b1dbe57d4a2d3499206e743736185ad83b7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:050568810a598089749dfd041ed8907a541712518a68a35e552570d78c637f2a
+oid sha256:636afe470df34298aade5683aeef32484837b94673bdd200b774ca2cd082f9da
 size 4040701744