Run 4. Outer Step 62. Inner Step 34.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611620,
-    5611624,
-    5611628,
-    5611632,
-    5611635,
-    5611639,
-    5611642
+    5611647,
+    5611651,
+    5611654,
+    5611658,
+    5611658,
+    5611658
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d339d8c5e3d720fa2b06651e04b5ba9b86ebfc663ef178fa78abecf892cb6c
+oid sha256:2373d37cb9e45b0fddb39a29adef7b5935a8055e56da76a62e850cc2d6f4395f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3894f50e170479a5e0bc1488e75f5c791e77c701e020dbdcdb273d43ea981ca9
+oid sha256:537ff3c84388abd006313bab122d3dd76166ea60ae67fcfce41fa0250add69dd
 size 4040701744