Run 4. Outer Step 58. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586864,
-    5586868,
-    5586872,
-    5586876,
-    5586880
+    5586885,
+    5586889,
+    5586893,
+    5586897,
+    5586902
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5583387,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4e88ec5ff40047dc0c73a990873dc528c7e0873c53cbff873640e917928c1f
+oid sha256:650848d354cf8281286df2c64e61d12096c51456cc9b510b840871d8cf966187
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf9b6666cffd2a5a7b9fb77994e174294c6f3c5b38eb247ea05e11fbe9b7eb3
+oid sha256:c9e216af5d11dbb3efa7950e27d480ff409cbda21e9397d444af7bf893de2d7a
 size 4040701744