Run 4. Outer Step 95. Inner Step 25.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5689697,
-    5689723
+    5689751,
+    5689777
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5673692,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8dc5e5f57b6376010d3f1310997034cbecfbf08ed46bcb24e27daa1c78ffc2a
+oid sha256:e7ce01e1c9bb1ec1a8794389fce06a439bc1d9b141552c1b75f777576a1c8cd3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae32781e84b33d2ea5320685525a9237712c1632252a67c846587c7503a6269a
+oid sha256:45e5da08e746edaef5606a1ce5da5f3984b350a46a7db54e6990537e46bdc27f
 size 4040701744