Run 4. Outer Step 54. Inner Step 86.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580270,
-    5580272,
-    5580274,
-    5580276,
-    5580279,
-    5580281,
-    5580283
+    5580287,
+    5580290,
+    5580293,
+    5580295,
+    5580298
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 85,
+  "inner_step": 86,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5dae5641774b5905ee7ecf7f3a321f79dc58eb1500801c6ae689127b8d91a0
+oid sha256:6ab700daeae7d8d7273baca270cb4753b3546fbca6f274538d6adec979d3f291
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea98d122e6e9b14b392ceb383525f42e2a5a853646794ea10760a68c3cac4eb
+oid sha256:532772bdb24666e8b591c8b26ca28de7d42033eeefd5ac828daad38c80c12239
 size 4040701744