Run 4. Outer Step 63. Inner Step 72.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5646501,
-    5646505,
-    5646509,
-    5646513,
-    5646517
+    5646522,
+    5646526,
+    5646531,
+    5646535,
+    5646540
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 71,
+  "inner_step": 72,
   "inner_steps": 0,
   "last_allreduce_block": 5644286,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b25d900f80324ed7e77de6df5353e9f9aef3a2da90e19f1e3de8c3a5e0b28799
+oid sha256:9c88aba1c84cf2cef829b5083ee9ce92c7b3141727a2351e92fc2b2e481019a8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0382db78495339f14b667a6476ebeb815ee70c1cba99c189f54ba78fcfa11c
+oid sha256:d913ff8f15006538c2445be90fe3957ced5836d4cd13adf1c068cdacfed24ce5
 size 4040701744