Run 4. Outer Step 53. Inner Step 130.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5590470,
-    5590474,
-    5590479,
-    5590483,
-    5590488
+    5590492,
+    5590497,
+    5590501,
+    5590505,
+    5590510
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 129,
+  "inner_step": 130,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3edc0ca3768c29d0af7666b035f09fbaf59029493ae51cac2b4b03b7646270d9
+oid sha256:994055d0b791ecb3d32babe70b4953d0cf2a94439d80187e245c0ac22e601c66
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06982f4f23ec0c48b51c5de243b6af63f1068cd893bf62bf00ffd66aa0bf3630
+oid sha256:854db2d143ae7d99a430ae19b005538a06154bb41db0920e1e06b7bd3cdfa1b5
 size 4040701744