Run 4. Outer Step 18. Inner Step 24.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521791,
-    5521795,
-    5521799,
-    5521802,
-    5521806,
-    5521809
+    5521814,
+    5521817,
+    5521821,
+    5521824,
+    5521828,
+    5521831
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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:aaecba50986d92a0365471e69ee199e1be38243731805c2c83df1e3f314c1868
+oid sha256:7ccf841127a79d646286b0542181fff33ad6819adc663393e38f39fafc65589f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5153e58c4287bdc84a66f1348be24f719ba2d43ed6d0c452c24a770180d4a1
+oid sha256:9b3d3b00039090a96060de1d0c8d53004730df88053e616a8fcdf55adaa57fdf
 size 4040701744