Run 4. Outer Step 54. Inner Step 93.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580334,
-    5580337,
-    5580338,
-    5580340,
-    5580342,
-    5580344,
-    5580347
+    5580351,
+    5580353,
+    5580355,
+    5580357,
+    5580359
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 92,
+  "inner_step": 93,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37a2c888df08428d4fceba7b39cd0bc58371186ce03ae685f7ad1f755b5ddc9
+oid sha256:91e8938624c73171a909abd0e70243a22b292139a6390d0c815e6befce072395
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e45c2296d0eea04c2d18c954ebd812e8d97cbd2e354bf6321ed8a3afcc13697
+oid sha256:746eea640aa826704e36a75aff5ddefed4cb24d0e2b918ec348e9aabaf021618
 size 4040701744