Run 4. Outer Step 66. Inner Step 96.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621956,
-    5621960,
-    5621965,
-    5621969,
-    5621973
+    5621978,
+    5621981,
+    5621985,
+    5621990,
+    5621994
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "inner_steps": 0,
   "last_allreduce_block": 5613899,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001d7d6d38c2a5f4c3d0ee17f4e25a44624dbe36f5c0063904d64d718bdc1271
+oid sha256:1e81ddae99686f4f4635c04ab968819cf7c2dfbebbd7120966c51b45ab3d8248
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e7c86e15a383664127f1dccb6d3c68beb9525c9d31e24c7d9e822a30231f8d
+oid sha256:4da2f2a0646bb4170f50af481cf41cb47174bf278eb85b74f3c42fac8cdf1656
 size 4040701744