Run 4. Outer Step 57. Inner Step 30.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602050,
-    5602053,
-    5602054,
-    5602056,
-    5602059,
-    5602061,
-    5602064
+    5602067,
+    5602068,
+    5602071,
+    5602073,
+    5602074
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46550f5669116015c3f44c6c3da473b34a0a595980e072b4dbbbc34889f4a052
+oid sha256:b8ab289de22c88da08e045b159b147564c1539d6e19fd15a5db7348dc3b6d67b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65b3f8137dfcaa4aba0f7da51b2a8dbb93b4f2ca7ca454e5502102c7d66afdc
+oid sha256:d32905611e7b9a6852e9018455f0a635e1263d4c633cd614ef5dfbbb257c895f
 size 4040701744