Run 4. Outer Step 66. Inner Step 93.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621891,
-    5621896,
-    5621900,
-    5621904,
-    5621908
+    5621913,
+    5621917,
+    5621921,
+    5621926,
+    5621930
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 92,
+  "inner_step": 93,
   "inner_steps": 0,
   "last_allreduce_block": 5613899,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b35e61f6fd269a23698d5142566e698b51aa8c0286f66d93c840399ef9fd99
+oid sha256:db425dfe92508149666c5ba398c211aec3ef3ab5a8dd97abbcd352bc898f2810
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00c9f8805abb70691a54c462ae1a6e2139013f61dc3451121a4aede546e9b2c
+oid sha256:c4f411c8e368409ed1f70933a691c72b406e43ff756f8d210efc7d76c9815f7f
 size 4040701744