Run 4. Outer Step 85. Inner Step 0.

config.json

@@ -268,15 +268,16 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5674888,
-    5674917
+    5674950,
+    5674980,
+    5675011
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 40,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5672513,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066d70d49077a9dc08937cd2eccc5a55ed0d18358974757705fb8624ff914dbc
+oid sha256:75b9652632af0917a48a3ba102e1100e6295cdf559d18418d17f7251e9bf283b
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aaa7c3dc8ff4b203dbeade4e0ebb94bb3c640e61ac9839142d5670749f741e7
+oid sha256:c8e2d930f726395a47a0a12c5dc7168df07d23382d86b5604b982725eff481d3
 size 4040701744