Run 4. Outer Step 28. Inner Step 24.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537708,
-    5537712,
-    5537716,
-    5537720,
-    5537724,
-    5537728
+    5537733,
+    5537737,
+    5537741,
+    5537745,
+    5537750,
+    5537754
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5531651,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb1d189115c9bb46da6a4f39fed7e2cd5616970fff4e79434cbd3d60af17f85
+oid sha256:a8949da2a76ff780c68aef7f272c8a00992ce7d25464d3c000c603a61ba82ac9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df25edc03bb16c21b034c0d10eaf4a2f95bc6d18d790b4d623414cfc78c0069d
+oid sha256:c65b82a1970cea080b1b166cc60654cbf695df76c1dc3f1f6a30c04ad588da61
 size 4040701744