Run 4. Outer Step 28. Inner Step 42.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538414,
-    5538416,
-    5538418,
-    5538420,
-    5538423,
-    5538425,
-    5538428
+    5538431,
+    5538432,
+    5538433,
+    5538435,
+    5538436
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:341dfb9ed58db92aa4593b33044bc3c1bd7a520adce7c69420279a49ec4c6d31
+oid sha256:3d4a176725f4c15977c671bdac263074ef4db611e5ba4fa1c3e88a2339ef8d22
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8754216c166626f643e09b968ae785623723824736463c02cd2045882b52e331
+oid sha256:dc8a303049e5612397060d9cfd0545299110e6b7fc24ffdf87d9e3adf1e080a6
 size 4040701744