Run 4. Outer Step 57. Inner Step 26.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601922,
-    5601925,
-    5601928,
-    5601930,
-    5601931,
-    5601933,
-    5601936
+    5601938,
+    5601940,
+    5601942,
+    5601943,
+    5601945
   ],
   "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": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e20d658a37ce6f39cd82bea2aec09422c3d2eefbae96bcbd72278ab89663fb
+oid sha256:6afaf683da1381b8bbf407e9b4c857f2aeee5b96041f6b0aff76bc4230755c10
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22e0b20e4017e7777c2055615d7a5fcf66aad528538d48fd08fbda5e78ea49c
+oid sha256:079d4cf81b15a74d17c4dc9f8d85bd513dfabd4433928bee610d463195a01303
 size 4040701744