Run 4. Outer Step 35. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548628,
-    5548632,
-    5548636,
-    5548640,
-    5548645
+    5548649,
+    5548653,
+    5548658,
+    5548662,
+    5548666
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcbbc96edc80cf6c9ccf9b59ede935131b5a4dbdf8a005bafe7b2b17e878c289
+oid sha256:384188b3f5186a223d5b4af3f95184296843dc773a07c57937781d1882e44245
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f50a4a9695447768efbe6596d4b4007fed82a2d27652c9231d013bfff6be7bc
+oid sha256:67aae76c4cd38ea09f30d025a69bac8f78dd43ec9d37671e31176758fc3828c6
 size 4040701744