Run 4. Outer Step 15. Inner Step 80.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515478,
-    5515482,
-    5515485,
-    5515489,
-    5515493,
-    5515497
+    5515501,
+    5515505,
+    5515509,
+    5515513,
+    5515516,
+    5515520
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af596f07a2b2d8cb8670a8a4b2f26c84341aa9708a0a6c50020d158c3a4be12
+oid sha256:72464e2f38f4ca04ad9779c323ada3c4e6e7bead93f87412f8ba1bae3d080c37
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968205e482363b8d3c14421dc1893addd58e4cbc212c2c595f422d5dde5bd5d5
+oid sha256:b8a59936b5728c04da8cfc8337c0a73c72e8e08088458a48534ec54e95c6dd5b
 size 4040701744