Run 4. Outer Step 53. Inner Step 35.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577358,
-    5577360,
-    5577362,
-    5577364,
-    5577366,
-    5577369,
-    5577371
+    5577375,
+    5577378,
+    5577381,
+    5577383,
+    5577385
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "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 sha256:46cf059e1aa78c8248943f6dd2269b24a1fecb70e7c625ff5793b235dfc80617
+oid sha256:dcaf982dde8908babdc61d4d6822cb9589ef9722c04462b24b5c157e35a36b5c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ead76482df39fb60e401ece55c306e99589b5d8fdc3407c36b87842a807ac6
+oid sha256:4408b52ed9a8f3f832fce613eb4cdb74dec6b7a6d893b3abfc6dd2f86dff7881
 size 4040701744