Run 4. Outer Step 57. Inner Step 34.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602016,
-    5602019,
-    5602022,
-    5602024,
-    5602027
+    5602030,
+    5602034,
+    5602037,
+    5602040,
+    5602042
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922e0ae5a6f7646c964ef25d33185ac523f979d7dc24970c4ec3d180bfe6c0ed
+oid sha256:9e1824c8719acf341daa6047dca6defb9ae13a6247c674df9cc84ddbeeca7e07
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e505ff710af2b410c881c4b1e82f151b26fc22fb2838cb48707b72158fe4b4b
+oid sha256:bbafb240b8bbaffc3077aa1a79b49e63af99893cbbcc2ab8f18a14e3209522b4
 size 4040701744