Run 4. Outer Step 54. Inner Step 92.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580318,
-    5580320,
-    5580322,
-    5580324,
-    5580326,
-    5580329,
-    5580332
+    5580335,
+    5580337,
+    5580341,
+    5580343,
+    5580345
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 91,
+  "inner_step": 92,
   "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:e6d69977236e2d6da8acbf8268a3ce5289a8ecf9732efdd2844187e30716603f
+oid sha256:9c2c72a8d6ae863013cd6360f764ada915d1095f886a2e377f66e7f3e0a2c0e4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c1daa54d3e5afa5ae07cee15988a970c478e400635f2a0d3dafc1401c88912
+oid sha256:c5406cb577d0e7d26cea4e1af2e45f633e0ee867b5c9b95ea4f95e5dd683ced2
 size 4040701744