Run 4. Outer Step 65. Inner Step 89.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650385,
-    5650415
+    5650444,
+    5650473
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 87,
+  "inner_step": 89,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b6a19536e810feddc5dc214ef3835e75396b8eb41bc8a6d9cb234b43088ead
+oid sha256:ce055985e2da0b2d56f81fdefffd33cf1ff0b389e49451c9f198e21016ea10cf
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0dcee8c43e4605791b8ee2101abe904293ba72f8acb1495a3254e8c97955711
+oid sha256:0174273069cc9ca220321f577c1fcd1bc5b29022c07dfa8c36f06fb60dc16ae0
 size 4040701744