Run 4. Outer Step 43. Inner Step 83.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563394,
-    5563399,
-    5563403,
-    5563408,
-    5563412
+    5563417,
+    5563422,
+    5563426,
+    5563430,
+    5563435
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 83,
   "inner_steps": 0,
   "last_allreduce_block": 5560919,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a36918a57a9859e148d27835401bc1879667833f2c615a8ae0b300ae350a74be
+oid sha256:978d805c5b3c7dda48665bbca0edd103504a3ea4cabdc73816f4bcafb777955b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a2c1ec69531db39540639a9ec916b3da42e47999025f0b7641d1b13e0b59c7
+oid sha256:383d8e7f5cea537835e4aa79bcb630458809f61d73d78d41935c70d14fcf9400
 size 4040701744