Run 4. Outer Step 57. Inner Step 27.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601965,
-    5601968,
-    5601969,
-    5601971,
-    5601973
+    5601976,
+    5601979,
+    5601982,
+    5601985,
+    5601987
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afaf683da1381b8bbf407e9b4c857f2aeee5b96041f6b0aff76bc4230755c10
+oid sha256:5de9279973cbf1b8cf675b855f2d44a27efbe270ce3b097564c4fe6f7690a711
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:079d4cf81b15a74d17c4dc9f8d85bd513dfabd4433928bee610d463195a01303
+oid sha256:76873f684a88fb97378338021db44770b161ce5f15f059bb3aed875fda6dba30
 size 4040701744