Run 4. Outer Step 28. Inner Step 40.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538354,
-    5538356,
-    5538358,
-    5538360,
-    5538362,
-    5538364,
-    5538367,
-    5538370
+    5538373,
+    5538375,
+    5538378,
+    5538381,
+    5538383
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63109bdd9a57f7d4b5c396f67dd1bfee0b67ce251d0460803ccc7c932111c512
+oid sha256:508a85389ebd529deafe182858e1d8c342c76f8f15967f13be44ba10db43af64
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52140a6fc80b2c864dba247b5d5cc25edb6a801fe960d08367ea761a955cb3f4
+oid sha256:c98e28e8f0afbaef8e524cac10dc50cc58ad39d94671282c52256b92a722d21a
 size 4040701744