Run 4. Outer Step 36. Inner Step 11.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549840,
-    5549843,
-    5549849,
-    5549852,
-    5549857
+    5549863,
+    5549867,
+    5549872,
+    5549876,
+    5549880
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136eab7778982a9a48fa8aab233e061c297545a8e1c855ba47876f53ba57656b
+oid sha256:08f60d302b7625ed07e85a21ad98dd82f4c6b3a8f3aba54fb15763e48c547263
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c405a975df8de176bee75bdf1ce83b6fa68150c52d3a390be2e0b1ffebb613
+oid sha256:50b9660bceb5f7c7affd6e547f13d7c32eec87d8a29058b2d9937b0913f9e726
 size 4040701744