Run 4. Outer Step 62. Inner Step 33.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611598,
-    5611601,
-    5611605,
-    5611608,
-    5611612,
-    5611616
+    5611620,
+    5611624,
+    5611628,
+    5611632,
+    5611635,
+    5611639,
+    5611642
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "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 sha256:57ee12f8f7cc7a8c84bb0e1c35c24887568bd4eba4662399d21757076d02b5bd
+oid sha256:12d339d8c5e3d720fa2b06651e04b5ba9b86ebfc663ef178fa78abecf892cb6c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4929726f680a8d9873bc9417b94a96753a7005f1a98579ad9968881848b50d7
+oid sha256:3894f50e170479a5e0bc1488e75f5c791e77c701e020dbdcdb273d43ea981ca9
 size 4040701744