Run 4. Outer Step 57. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601200,
-    5601207,
-    5601214,
-    5601222,
-    5601230
+    5601238,
+    5601243,
+    5601250,
+    5601258,
+    5601263
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "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 sha256:2d89772b573104a753c1ce9265e34c779f8e40aa7796e166211ce3f782b99ef8
+oid sha256:d377640ff530258fb2b69ed9f87d431ebb845c146b8cc13d15f285f43d11a967
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47968df210d16370c4d61705989c30d7709ebc158dfe880a7cf58c503449281
+oid sha256:852ceabeec50e1245bdd3d4da0047b1fcfc061e3a823ed51da2926780c43eceb
 size 4040701744