Run 4. Outer Step 62. Inner Step 26.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611431,
-    5611435,
-    5611438,
-    5611442,
-    5611446
+    5611450,
+    5611454,
+    5611458,
+    5611461,
+    5611465,
+    5611469
   ],
   "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": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6ed91955a70d612be2fa51baac2212402503c96b122d082d1812373e27a8d0
+oid sha256:6efcc19aa5f82b611367759a4bea40b9b1b866b85191e64f2b35ae769bbf70af
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aacfb51911fae75fc09eddd4d43a729979f8f345931c6d50e03b2b8f90a8c12
+oid sha256:1f84ddae8cc818952f42cef8d9e1b2c446d726ecd0a1375a09ed73862cd680ba
 size 4040701744