Run 4. Outer Step 29. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539477,
-    5539482,
-    5539487,
-    5539492,
-    5539496
+    5539503,
+    5539507,
+    5539512,
+    5539517,
+    5539522
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73275451018de7e8948b566a0709e1ceb87fad21ab3f77bfcda9fb8faf34a90e
+oid sha256:0361dbc4fd2780180af86b275517a57edc7461d5f9eb4225e1c354c5cfb91a5f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef174ebcdbf726da4802eef535acf72eba911aaf9b3cb3d34baa035b8d91fca
+oid sha256:796ae28f980dcd4e44beccbd85d4b95b034304e8133b2364769650ea86dc06a4
 size 4040701744