Run 4. Outer Step 60. Inner Step 2.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607413,
-    5607416,
-    5607418,
-    5607422,
-    5607425,
-    5607427
+    5607429,
+    5607432,
+    5607435,
+    5607437,
+    5607440
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "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:f3d5e0ebfa63db0c0fe2b05572506347a57306e9840709aad9502ef372a54a93
+oid sha256:37c78c6d4bb38dcd0213750719ad8f9e5e23b00548559a661c66c01b5acfb1b7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fb0fef3a7ebd0b725cc292d3b9de9683d2cf5a08328565e5dad4b6a5b60c26
+oid sha256:b032b92f3312dbd94b36a6f985215da71232cb396eaa6bd60b65a30252946c4e
 size 4040701744