Run 4. Outer Step 24. Inner Step 29.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5532416,
-    5532419,
-    5532422,
-    5532424,
-    5532425
+    5532428,
+    5532431,
+    5532433,
+    5532435,
+    5532438,
+    5532441,
+    5532443,
+    5532445,
+    5532447,
+    5532449
   ],
   "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": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8735b83a6461ad76dadd06254296b5dd1e2e15f48361bb2f42a06025c6021dde
+oid sha256:11d7ab2b6208692635fc94f72ed646c0fa9372890ec18ee62e96a182164aa2f8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1ec6ddccb0b65138821bdf70ffddc6183c5fa7a22dea69d756fdad4b64393d
+oid sha256:9d63619b7dc34cc748b6e81e8863ff2a90c2328ac490ae8acb667787b33c91e4
 size 4040701744