Run 4. Outer Step 3. Inner Step 136.

config.json

@@ -268,24 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484802,
-    5484804,
-    5484807,
-    5484808,
-    5484809,
-    5484812,
-    5484815,
-    5484817,
-    5484819,
-    5484820,
-    5484822
+    5484826,
+    5484830,
+    5484832,
+    5484833,
+    5484835,
+    5484838,
+    5484840,
+    5484843,
+    5484845,
+    5484846,
+    5484848,
+    5484850
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 135,
+  "inner_step": 136,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bfd71cd05cbd07d5771e5c5d792a43376615c243949636c8d8e1410e8b2f009
+oid sha256:afae4fcd755072526d22fa84c3afba9b16916ecca4760e46f0bedf1185f165c0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851a842fa166e42c29fd4be6b0da48b9bf150f8ae550da830ba3faeba24e85e5
+oid sha256:1e34ea93104165a4c3179bcd440552452c39ebc298a8debc23e23c5fdda60216
 size 4040701744