Run 4. Outer Step 21. Inner Step 19.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526075,
-    5526082,
-    5526088,
-    5526094,
-    5526100
+    5526107,
+    5526113,
+    5526119,
+    5526126,
+    5526132
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb651048d1add2de49ad124a58cfd28ee83e0f6adc1cdce3b62ae1dc73df7652
+oid sha256:672f54e0ed8838d352531cdc71092a06b042e13954b2ea015808b56e74014175
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf41a67f2f863c526d5ccd724580cc2e600983532c3d8ab7a36524e91e4e8c25
+oid sha256:6b46ca2e57414b68c7f6c499f44e5192b2190c9c0e20be265ff32122910378f9
 size 4040701744