Run 4. Outer Step 58. Inner Step 20.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5605065,
-    5605070,
-    5605074,
-    5605077,
-    5605081,
-    5605085
+    5605090,
+    5605094,
+    5605098,
+    5605102,
+    5605106,
+    5605110
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "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:e4f2f24b6cecc1dd700dba54f8241335374a573537cc17f3ddebd6fe32b926e5
+oid sha256:1e6fb578773f8a92ad6c5a768d8698c4993f040ecf687003c03084bdb300cd76
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060422082528a3c00c51e681007ebef0c539621c2bcc1e13f8b989e38753f02b
+oid sha256:c462d855eccf16068a959db9ba91779930a92023b67096ab526e85335505b5be
 size 4040701744