Run 4. Outer Step 54. Inner Step 95.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580391,
-    5580394,
-    5580396,
-    5580399,
-    5580402,
-    5580404
+    5580407,
+    5580410,
+    5580412,
+    5580414,
+    5580416
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 94,
+  "inner_step": 95,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f6d7151f60d07d89c8ef84a92eae4a3462128e04031829c538ae179b561215
+oid sha256:fdcf69b73ee25b9a8e45e2799f277595f80821d6c29266752af7d55c8889156a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449a9d3720c44ba2624e7f8312e392735f59bdff0959b1c6d253324d8c00d434
+oid sha256:26fb9426d611f4957aac4c09dffd808a80e6d28fd6b5117f1929c0329fb131bc
 size 4040701744