Run 4. Outer Step 54. Inner Step 62.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579416,
-    5579418,
-    5579421,
-    5579423,
-    5579425,
-    5579427,
-    5579430
+    5579432,
+    5579434,
+    5579437,
+    5579437,
+    5579441
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 61,
+  "inner_step": 62,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecc0d73e2adf122d6890a994168a13418a38dfad119f6b076aff1874b002aa9
+oid sha256:5ed2332d1c54bb97b25a581601f81f39de439e76da24fca8d958f135ca6c31c5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cbcba0c5698f6d06006b65ee6dd71f95fa5bcc1f8a2ac9b9e95c0869a53335d
+oid sha256:ac7c0e6db66f1ce6bf6785927b05ebb225c355d01f8d9d28f17951075f045c12
 size 4040701744