Run 4. Outer Step 58. Inner Step 68.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604285,
-    5604289,
-    5604293,
-    5604298,
-    5604302
+    5604306,
+    5604310,
+    5604315,
+    5604318,
+    5604323
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "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:df8344f9e121c6f4f0201258d344c998edafd73eeda886ed815d1e466c541052
+oid sha256:167f867dabad8796805b146d6d4cd93c408e5a9a3dfdf6c9659fd00567b37f6d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bd10a894059ad8d4fa741d8e3de52164fb003e4231ab107d4bb9cfa4a545286
+oid sha256:3322e8dba7e6a93bb53d782b88480deacca9bcaf196566d45be7ba58506cdbd1
 size 4040701744