Run 4. Outer Step 53. Inner Step 35.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577350,
-    5577353,
-    5577356,
-    5577358,
-    5577360,
-    5577361,
-    5577363
+    5577367,
+    5577369,
+    5577371,
+    5577373,
+    5577376
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123862f6058d9b9eae72db1d837885343048b17d9db2739df9545dc654043a2f
+oid sha256:3466f6f10849c98795d3a105805542b4c39ff642ab53a933bb79409a21753c87
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40dfd341ffa8cce0a3e8bcbf6f317068d88ea21d01f483488985fa12e100387
+oid sha256:5ca582d8f57ee8e385942b2526cb5776291df24aecac298bc172a2698396d7cb
 size 4040701744