Run 4. Outer Step 66. Inner Step 94.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621913,
-    5621917,
-    5621921,
-    5621926,
-    5621930
+    5621934,
+    5621939,
+    5621943,
+    5621947,
+    5621951
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 93,
+  "inner_step": 94,
   "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:db425dfe92508149666c5ba398c211aec3ef3ab5a8dd97abbcd352bc898f2810
+oid sha256:ceef1d31c3c70bcacbc7265a5bd1def90e7cf7f1ebcb0936ab04cedf00c3abde
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f411c8e368409ed1f70933a691c72b406e43ff756f8d210efc7d76c9815f7f
+oid sha256:b2366822bb17821e691fb0cd8d29aaf4a415c62471580a85944f602a53e13e36
 size 4040701744