Run 4. Outer Step 60. Inner Step 13.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607633,
-    5607637,
-    5607643,
-    5607647,
-    5607652,
-    5607656
+    5607661,
+    5607664,
+    5607668,
+    5607672,
+    5607676,
+    5607681
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456a557b3a22aac97b6e36adc332900b3c42aa8563f6a82bc61b532ad560bb41
+oid sha256:0ae5acd711785dee5384bd54a9cfeba37a1dcf4799e6ee22644303a5da77264a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e8c1dc2d06516efdb2c9028b0050f003861b2faee83e2ca4867506aac8640d9
+oid sha256:9cb2fc7eaa40cd0cb6752688a5cd94ec5102101263774b74453e8fadcafc54fc
 size 4040701744