Run 4. Outer Step 21. Inner Step 29.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526488,
-    5526494,
-    5526500,
-    5526506,
-    5526512
+    5526520,
+    5526527,
+    5526533,
+    5526538,
+    5526545
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2d75315b82588ca4dbe4a49087354ce90d8715b960b9bcfb939d96ca911578
+oid sha256:bb3e62f21333eb1e3d5325f4f840cec53d75e1ce1fe467fb286a780986452308
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4f138f07c192e2120ef87d639b9d7bc7229e70ca8b7bf35493052978bf9328
+oid sha256:435bbedf16984eafa21410dc4c1188f199dee2ffee1fd963a524be872502745d
 size 4040701744