Run 3. Outer Step 9. Inner Step 135.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5420947,
-    5420951,
-    5420956,
-    5420960,
-    5420966
+    5421003,
+    5421008,
+    5421013,
+    5421018,
+    5421023
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 133,
+  "inner_step": 135,
   "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:c0e2b99d19c814510b8b05be9d6e38e47794692a2c0309d008e05558336a3bc9
+oid sha256:f125642ebf123002aaf5ccf41e6cb742afc35a39f590d1916a5bbeca9676ade3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35922e3995af06910084823cec55a568d46a9166214b6140c23eb3c6d6d5b78f
+oid sha256:2c004c8f329d64235d65ce41380a9c3892eec0b7159b8222694c02103491c82b
 size 4040701744