Run 4. Outer Step 33. Inner Step 25.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544757,
-    5544759,
-    5544761,
-    5544764,
-    5544766,
-    5544768,
-    5544771,
-    5544775,
-    5544778
+    5544781,
+    5544784,
+    5544787,
+    5544790,
+    5544793
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "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 sha256:2bb237e817aa8b623e30db90ecf6841fcb41ea7e7fc59f8032ca94b6a9d1a1d5
+oid sha256:13c22669ee9369ff0715c7d0995f34f601f48420415ab9714c13183381be9cd4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1240755edd8c8cc1cd2cf28bec89678f801e3a528a9e491979192f9ade4cf1f8
+oid sha256:cdaa35574d26f8f90bf77ea989942abe9224ee886a700e616fb365b5f2ae78c9
 size 4040701744