Run 4. Outer Step 0. Inner Step 5427.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5593723,
-    5593730,
-    5593737,
-    5593743,
-    5593750
+    5593757,
+    5593764,
+    5593771,
+    5593778,
+    5593785
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5421,
+  "inner_step": 5427,
   "inner_steps": 0,
   "last_allreduce_block": 5470731,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032f1de2057178e43e17e90da3518372c181a4f077d53834fdef5bc75b938ca9
+oid sha256:69b9f0cef3f42fa0897d7d1c8683a8562619040d7a74f9842f418e4b85e6b7cc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4d0c839742e693cd9a7ba133246bdb79c1ed83889b5c4548722128b79353ac
+oid sha256:ca63b90a173323d9576c970891ebaed2c6efeaad8202b7e4929ef06bed1da5e5
 size 4040701744