Run 4. Outer Step 60. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608120,
-    5608124,
-    5608129,
-    5608133,
-    5608137
+    5608142,
+    5608147,
+    5608151,
+    5608155,
+    5608159
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b94eebb6a2404ae796c84e0b00e4cd868587c05b6be0f6694602259e7dcd5a
+oid sha256:c0861d8fcfaeb3ec5fc4a6a880e2e5f4250bc1bea891c617f015532f378e0ff2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e3866259fecc08106eed3cc4711b59d79da912c17eddacdd6eda412ae8c0c4
+oid sha256:0a6a88cf239bde1780d2f5d05b04a245563f13088fbe1f8a2a172385efa91246
 size 4040701744