Run 4. Outer Step 29. Inner Step 17.

config.json

@@ -268,25 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539049,
-    5539052,
-    5539054,
-    5539055,
-    5539057,
-    5539059,
-    5539062,
-    5539064,
-    5539066,
-    5539068,
-    5539069,
-    5539070
+    5539073,
+    5539075,
+    5539077,
+    5539079,
+    5539081
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5dc4b81c91d4aac6d2e99da581730e29afa04342cd44a475dfffbc585a4b95b
+oid sha256:9b8e62013309c8905caf5c97b61a4f3fc5f5e3f1682fa90b3e6bd478dd406862
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fa87bb210ff0b37aabbfab9cd2441ec6320f062835dc7f5e98c0c529efcb0f
+oid sha256:ae0d0c2ef754c9c57c9d09354db29f49b6bca43bedf6013b593c04f728634a90
 size 4040701744