Run 4. Outer Step 46. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5567256,
-    5567260,
-    5567264,
-    5567268,
-    5567272
+    5567277,
+    5567281,
+    5567285,
+    5567289,
+    5567293
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea11ce80298e9c78863506a41ccbb869aff338a23d85ff283e714acf84ec105
+oid sha256:7382a2e199f9ef6bcce28ff3b734d86e91006315da64ee39eab5418fb8bd7917
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f2df9f18db94bf3f72ccf7ac0bca451644566bba2d637aacfa6d344a17f2bf
+oid sha256:33462fe60c5c6defe5043d5e09d66c6091d603a881ace73ba6fc78f0e6db41e6
 size 4040701744