Run 4. Outer Step 7. Inner Step 53.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494141,
-    5494147,
-    5494152,
-    5494157,
-    5494162
+    5494168,
+    5494173,
+    5494178,
+    5494183,
+    5494189
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 52,
+  "inner_step": 53,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:896b366f9533c0609e176d3ee7c2115ca5bd1793cf5ffc6a8ad007036877a01d
+oid sha256:f26e3788989366ff8c82fef43ba1c3e0967753a711da9d6cb43b226d525e4a17
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0742a8a93ca47875f26a02025df918ccd9296f883a893e4abba2fe6d12ed7845
+oid sha256:65703cdfe68c39ef39bac172326f4cf8c2097f9a590236e2fd3890b6d151bbe5
 size 4040701744