Run 4. Outer Step 62. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610926,
-    5610931,
-    5610936,
-    5610940,
-    5610945
+    5610951,
+    5610955,
+    5610960,
+    5610965,
+    5610969
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70afa28090a5e81990b2513332499a2f3c559ff7634e1f3eedf97faa2731e218
+oid sha256:55fdebce526089a1d46cee501dfaeeff590dbab689bebee6d3a5c02d58b65c82
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb139938914e02cb62e11a204c2d15dc5c4cff19e6b22112dd1c7e347edde244
+oid sha256:20027122c7d16b9476e9e00e80ab0e22bb88613eef4ad1b4dc70ab9578a0f0d2
 size 4040701744