Run 4. Outer Step 54. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580160,
-    5580164,
-    5580169,
-    5580174,
-    5580179
+    5580185,
+    5580189,
+    5580194,
+    5580199,
+    5580203
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "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 sha256:051bbb5734172e564c2feb75f5159db85010c13d16c564083b7eb7a5b600bbe2
+oid sha256:f6f2392a67c81454df87aca05c331efa5609ffd1f598e8b32b5b324962ef01ae
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806a10bdb470971692ee184cf766060bc6f1340013126af05accf3078c09222c
+oid sha256:a602dae1277edd0b8778180962e116c43c78de79991e1855460f0850b9fae179
 size 4040701744