Run 4. Outer Step 37. Inner Step 18.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5551666,
-    5551668,
-    5551670,
-    5551672,
-    5551674,
-    5551677,
-    5551680
+    5551684,
+    5551686,
+    5551689,
+    5551691,
+    5551695
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5550793,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbbd4d52a9418dd8a7ef41619fffe4702954b55eff53ba5e1a8d43de6834874f
+oid sha256:83aeb11ebca52920bd55bdd311bca69222c7536273f70a779e5d8306b54c1a2a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de7ec5da9985086755b0f871b8d077c89b0a1ddcb63b3a9ad076c04d63516b2
+oid sha256:9afe9d9abc0bbb12772d21077ba3a10423bcc93244a050a7d50bc5399403ae53
 size 4040701744