Run 4. Outer Step 57. Inner Step 36.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602011,
-    5602013,
-    5602015,
-    5602017,
-    5602020,
-    5602022,
-    5602024,
-    5602027
+    5602030,
+    5602032,
+    5602033,
+    5602035,
+    5602037
   ],
   "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": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c01fa2a880d9c97162b95925c93d795b2132d5937daceabc3769876ea72d9c
+oid sha256:d3f0fce284890ae581136eba76056bad5064aec1c661aadec680ff121db94e1e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133d32134e783ad289cd62d96f637212977b9b06e12ec0d784bb91765230860e
+oid sha256:d7dd6b2c86120ea1c0903de5f2005ab54bb6ccc2e2adadb2dc3143de1873c961
 size 4040701744