Run 4. Outer Step 28. Inner Step 20.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537684,
-    5537687,
-    5537689,
-    5537692,
-    5537694,
-    5537697,
-    5537699,
-    5537701,
-    5537704
+    5537707,
+    5537709,
+    5537712,
+    5537714,
+    5537717
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1be1b2471d241638a14f75eb12b4f5cfc9f075bf04b05c9d4525ebd3b1b216
+oid sha256:6a1f4bbc643ce51d1455dfb4564405f59b44531feaa7efe875777bc27ac605f3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04470f370ca59a4e30309ccd163d30eaf25f0a17f945174e4c951696a63a3932
+oid sha256:611c442fa978cdba9be9abba0048b1ccf0881ce7c8bd5b31a8f2ecbf6f39ad6e
 size 4040701744