Outer Step 8. Inner Step 316. Batch Size 448

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5293431,
-    5293436,
-    5293437,
-    5293443,
-    5293443,
-    5293449,
-    5293454,
-    5293455,
-    5293460,
-    5293460
+    5293513,
+    5293514,
+    5293519,
+    5293524,
+    5293525,
+    5293531,
+    5293531,
+    5293536,
+    5293541,
+    5293542
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 304,
+  "inner_step": 316,
   "inner_steps": 0,
   "last_allreduce_block": 5283755,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d422f1be0be593d81e9914d368886f6f17cdbde1cfe41bb1993254475ebf88
+oid sha256:290a857c61586984d9c3128bc96ab47bd7a87fa1d43ef42df6921cd7ee8ca6ba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56cc0a0eeebb4bcc0638279bc85bccfa5ae01e1b3758a3ef8353c555d96393ee
+oid sha256:d2b092c51da9033b4c2ca6b95e42cb72002cafbb51ac2a5a3e0eb38692bf71a8
 size 4040701744