Run 4. Outer Step 31. Inner Step 48.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542725,
-    5542727,
-    5542729,
-    5542732,
-    5542733,
-    5542736,
-    5542738
+    5542741,
+    5542743,
+    5542746,
+    5542748,
+    5542749
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc46d18b475424496233ff747b15b68d4664318781fea9fee765228c674be5ee
+oid sha256:fe2b5b1d5fb8fe9a5c8124cb31b9574d101be829bb154aec77a340e022b80076
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a756162fc6c0a6eebc6b06bb62a23985149ca84ec1437a6eefc685273880f174
+oid sha256:1d08fe3cd1f019e789f06700b4fe8b3fa1e9c4efbe2d86dd0c548f4288f3e60f
 size 4040701744