Run 3. Outer Step 9. Inner Step 987.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5420846,
-    5420849,
-    5420852,
-    5420856,
-    5420859
+    5420889,
+    5420893,
+    5420896,
+    5420899,
+    5420902
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 985,
+  "inner_step": 987,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c72ad52d45778d9b9f7f188229e52033355a480fdd34efb7511c0948e8ca153
+oid sha256:76cc3b371ae3fecc54574c15e2319d600826ac830c4284ebd6bdf5be453c2f99
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff0f00227de12da7f6fc4522e12dfd5af30f608a08da1acc557b6c449bc93c3
+oid sha256:e06d3095f7c0704ce979a5b0916d9a76d8d06ebf869c05719fc9eb73db9ad873
 size 4040701744