Run 4. Outer Step 58. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602868,
-    5602875,
-    5602881,
-    5602888,
-    5602895
+    5602903,
+    5602910,
+    5602917,
+    5602923,
+    5602930
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de124f268f0bfcdbf6713dcec75241185530fd7df2047cdc85bd9d456b09ed5b
+oid sha256:c4fd2d7812dddd0ab26c5b1dbc2c9e76fe0d336e5a45f0e5026d7c6765606eb7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f393add6d7cfe41e0f558e6812d880dd25331fe7b50ae7baffae6d587c772e
+oid sha256:3662e0f86ebc9e20fd32566084b915e1325862b0ec942da7830f6eda416945ea
 size 4040701744