Run 3. Outer Step 9. Inner Step 68.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5409838,
-    5409839,
-    5409841,
-    5409844,
-    5409846
+    5409880,
+    5409883,
+    5409884,
+    5409886,
+    5409888
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 66,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5f033d199bd147bd644f19a3f5f5720457a48570cb6f0ec3c5a30ee6305c43
+oid sha256:c21eef0b8b4aa94ffba4082d84fa247a9e1ae31814245582aebb56bf664a285f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cacfacfd081a6d46c34f378081765d8fdd9f0347cdf86130394f1306a9653a2d
+oid sha256:8080a9769fc904ff2a6353cf7f3cf10eb642c50560a683392a737f64465e6244
 size 4040701744