Run 4. Outer Step 25. Inner Step 42.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534618,
-    5534620,
-    5534622,
-    5534624,
-    5534626
+    5534629,
+    5534630,
+    5534633,
+    5534635,
+    5534638,
+    5534641,
+    5534644,
+    5534646,
+    5534649
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9ec27d800dd9cfeabb24805b976fb6bd45fab5675b1f2fc8df4572deb13b97
+oid sha256:06b2b27abcc6b201f9a4886ec4953a95a2eccee079122a24e472ccb48bc7aa00
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cce56f1e80fa91000db7b1974cc04f4e826b622a91282885249fc76f353f65c
+oid sha256:68380135b5982266940732dfaf9803ea74db02b12eb405aa432b27b617e0a485
 size 4040701744