Run 4. Outer Step 52. Inner Step 25.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575778,
-    5575781,
-    5575783,
-    5575786,
-    5575788,
-    5575790,
-    5575793,
-    5575796
+    5575799,
+    5575801,
+    5575803,
+    5575806,
+    5575808
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f093088e0a680246afdc57f1cf2fede59bb1b9c44619b0b24cc9753cd35534
+oid sha256:4e900766b999188d4804d5ad5635523e1cfb7377a2befba4601037a6013d68dd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c9d33bf5046906e7d75d640454de0a58e1ba6000271bbf8ca7d407102769ec
+oid sha256:82aadd2787db20a993986ddd70a5fd1a61a8769517120123dd371c47ec12b5b4
 size 4040701744