Run 4. Outer Step 53. Inner Step 36.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577449,
-    5577453,
-    5577456,
-    5577459,
-    5577461,
-    5577463
+    5577466,
+    5577469,
+    5577473,
+    5577476,
+    5577478
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c20a38348f1690fa8116da89e7191e9c4f3775a6821178530c4dd7bb14082d5
+oid sha256:8460338836ecc73fe9d20b9cce9b7c190f2acdd9ec1dfdbddcebc9b11cff86df
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9092c8de54cb0ed7fd0b39dab4164aa5aa569eae18a9f42de77c121bfc06f7
+oid sha256:0426a897b2838ea234dfe73b3c3802103c1c2c172d7e2089d66ad2f281acfbf9
 size 4040701744