Run 4. Outer Step 10. Inner Step 107.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506624,
-    5506628,
-    5506632,
-    5506635,
-    5506639,
-    5506643
+    5506647,
+    5506651,
+    5506654,
+    5506657,
+    5506662
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 106,
+  "inner_step": 107,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3b54223cf3fe20dad3378cd7c41275cb92f1a42ad69242077b916d332385ad
+oid sha256:83583e37b34474b9e0568f0ee49e617274641a0218d1621a3c0c8611d6ec16a0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84513b1815f0ae77a6bb267908f91f6df344cf893f58de9befa67b2eceb970d3
+oid sha256:2f15c398918b06e852c09a6cf2fe4a4d43946ebd91d8e76da4216b2e8d912ad5
 size 4040701744