Run 4. Outer Step 28. Inner Step 38.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538293,
-    5538295,
-    5538297,
-    5538298,
-    5538300,
-    5538301,
-    5538304,
-    5538308
+    5538311,
+    5538313,
+    5538316,
+    5538320,
+    5538321
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662be9ac4de6f01c14ed09451beb9e26a90499da0fbafb6f2c878489f14e4742
+oid sha256:ff7031f8e2aa163b05ea7941b043f1625315908191a7c6c6ed119d35c7051bf0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be568fd09fbc0e917e087838053bd0d964f36020b44320323acce425e14e2b3
+oid sha256:9fd60c8ae5e407c00efe0e0fb95660d6dc79d1d42c8ace35bd376d6bb9db4990
 size 4040701744