Run 4. Outer Step 62. Inner Step 6.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610891,
-    5610894,
-    5610898,
-    5610902,
-    5610905,
-    5610908
+    5610913,
+    5610916,
+    5610920,
+    5610923,
+    5610927,
+    5610931
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b50c574df8b4dc61df3ea36f0ff178371fa9a1fc5347eb15058db9cf3cff257e
+oid sha256:155d26e91a61551acc48410c2e9c3c6f131d19ee67b485197fdfd149ea0f4966
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e5a3b5a5c39064fd0be4289eb5a984c4bfb9216c7637a7f48157ad86015dac
+oid sha256:de0b7cf1393f1266c88a825cde44530cbc51d58706f3461d6fe8ead12694816c
 size 4040701744