Run 4. Outer Step 62. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610596,
-    5610600,
-    5610604,
-    5610609,
-    5610613
+    5610618,
+    5610622,
+    5610626,
+    5610631,
+    5610635
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8ccd815fe00bc11a44b9686c3b9994278da3f51363eee6033a92bfb877824b
+oid sha256:dc642716c19e755f1aff7d1c8ea564497572f8770a0709a38747d0a8997e4112
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee73e2bf6406812fd36b26ca5103caff9e3d01ba993165756382270a00a581a
+oid sha256:915ed7cd675dda808c5b7159e64d029a7bab43966425202eb79e69f66ae3e760
 size 4040701744