Run 4. Outer Step 40. Inner Step 48.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556433,
-    5556438,
-    5556443,
-    5556447,
-    5556452,
-    5556456
+    5556461,
+    5556465,
+    5556470,
+    5556474,
+    5556478,
+    5556483
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5553805,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f257243f8e16131ea85562503afe363ccbdc01178e5491daa47e97116271e33
+oid sha256:055d2f877da7cfb6580de32bac4de58b70257785023c108ed336300ee94ee9c1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2dd1c617a490a3c79b584f7367c97322ec276433e2cec03d44b92da0d9237b8
+oid sha256:6f32f0e4facd0250531fd3ab0b04580adb5f39e4689c9d5a5af57709a80f4c3e
 size 4040701744