Run 4. Outer Step 60. Inner Step 48.

config.json

@@ -268,21 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608534,
-    5608538,
-    5608542,
-    5608546,
-    5608550,
-    5608554,
-    5608559,
-    5608563
+    5608567,
+    5608571,
+    5608575,
+    5608578,
+    5608582,
+    5608586
   ],
   "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": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352cdd6623ce91caf8508ce660525f0b70e288d1f8a50ed37e4908331178e855
+oid sha256:1b7ee810ae3d34b9b5c8973014e4d45453c2b1b43fbc4e6cf997d210a8aea4f9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e8c910f71d530568cd00fbff6e4c0e7b27441e06d2dc3e405ecc45a3af56c6
+oid sha256:7d7dfcdca3eb7c7c57e3e0c02d9afd4b756a427f8740f41aaf179a76c7a8b3d6
 size 4040701744