Run 4. Outer Step 43. Inner Step 58.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5562549,
-    5562554,
-    5562558,
-    5562562,
-    5562567,
-    5562571
+    5562576,
+    5562581,
+    5562586,
+    5562591,
+    5562596
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 58,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4058078fc102d3297240752db02cd412c9df1f6c437e7f7794adf2c12bb109
+oid sha256:fb2d58f9b79d18b9dd0a9e99f8bf275fa3d0ca6ae6f809c87b5daf84c0450690
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c62d354d348060cf98c0922a70781ca3cbd8be4839f03b709461546979d722
+oid sha256:876645481c643a580eba1fe5625fbc52e85f6e863756516e7b7d496fe6157719
 size 4040701744