Run 4. Outer Step 52. Inner Step 30.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575907,
-    5575909,
-    5575913,
-    5575915,
-    5575918,
-    5575921,
-    5575923
+    5575926,
+    5575928,
+    5575931,
+    5575934,
+    5575936
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379f0900a9b224cff3a360d61c577b7cec15b54d9714b7ec612a1b9edd17cdd0
+oid sha256:1e0b2f99080a7827387563ffafd54baad17a9ba0cee5f841900844d870981f52
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41cb3ac4ef9084099c697001e520ae7897b0f4392f8c3bf73381ebf6537f5a19
+oid sha256:74be243c3b02cd8609cdc8f5def162908fa5333eed65d738a126f918642897f2
 size 4040701744