Run 4. Outer Step 60. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607909,
-    5607913,
-    5607918,
-    5607922,
-    5607927
+    5607934,
+    5607938,
+    5607943,
+    5607947,
+    5607953
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea6873b1a4661ef0ed006f5a53c91cb2a72bbfd51295d071b258b58ee9edf9a
+oid sha256:e0fb6a5b1c9b724e2ea3d112ee74f53ffe01d3f8b915512aa2acf15c6ae9634f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16525932a1c6356dfb8c5851ce2d4cbc4ad522f9fa3306a6d9cb0034c7766866
+oid sha256:3bd3ce1a719cf42bb8d9203c56f63b7ac7d66baeaa7152d4b6fef33108c2f7f5
 size 4040701744