Run 4. Outer Step 54. Inner Step 66.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579667,
-    5579669,
-    5579671,
-    5579673,
-    5579676
+    5579678,
+    5579682,
+    5579686,
+    5579689,
+    5579691
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "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:c81ab456500ffe674f116a643501ccd9b4d8b5e0aacc236cdd8088d6d79fa062
+oid sha256:102d2e0db0a23638309c84c35735a69476803daf902c4124f20aaf27c859c98f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699df9536ad7a17668422be3597c18a6c2b26365b10f25ce72c2ea2512c69315
+oid sha256:ccf6afa80c35d0ce5adbece344ead94ea437c49e8e721b549e57603ff1a403f9
 size 4040701744