Run 4. Outer Step 18. Inner Step 39.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5522176,
-    5522179,
-    5522183,
-    5522187,
-    5522190,
-    5522194
+    5522197,
+    5522201,
+    5522205,
+    5522208,
+    5522212,
+    5522215
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf718ae9d658d079aa1bb59e93f3b78d5e425a3daef8aa1b78e1b128c3bed6f
+oid sha256:56bc87284c7b3a4d612b2761a47f1697fc3d0713266bf05cb956ad44a6338df1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d69fedb8fcdf47128304ec7e038fe89d83e09b1bca01bc3bb81d3e7f6fbcc1
+oid sha256:d6ff72fa2c12be536df0f43d781c440ef984dc0b543bff262a8ef716731a5ba1
 size 4040701744