Run 2. Outer Step 3. Inner Step 125.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5331563,
-    5331566,
-    5331572,
-    5331576,
-    5331580
+    5331615,
+    5331619,
+    5331623,
+    5331628,
+    5331632
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 117,
+  "inner_step": 125,
   "inner_steps": 0,
   "last_allreduce_block": 5330632,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64b0acef7c053c91bffff78a704d9487d627d4cbe0f8b01d1a1dd282d683431
+oid sha256:d098d0e8d55cdc13b11446855563ac0b9409aae072bd067e98c478392e308ac5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b0b1647eb1a8e1c3caab429b64e81c2757d37290cd014da9e7475f54ed1578
+oid sha256:bef99c0b6d143844d15e15c9d9a3ae86650d1936db005075b34b03ae024bb766
 size 4040701744