Run 4. Outer Step 54. Inner Step 63.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579444,
-    5579446,
-    5579448,
-    5579450,
-    5579451,
-    5579452,
-    5579454,
-    5579456
+    5579459,
+    5579461,
+    5579464,
+    5579466,
+    5579467
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed2332d1c54bb97b25a581601f81f39de439e76da24fca8d958f135ca6c31c5
+oid sha256:ed88a5e62499579c54b9c47eb85572b64a5c0ab749a58de6fb5d2b3ded476212
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7c0e6db66f1ce6bf6785927b05ebb225c355d01f8d9d28f17951075f045c12
+oid sha256:c0f93458d228c872ae1d7504d4aadf2352cfccefecf56ff099f3b14ac1260350
 size 4040701744