Run 4. Outer Step 43. Inner Step 63.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5562660,
-    5562664,
-    5562668,
-    5562673,
-    5562677,
-    5562681
+    5562686,
+    5562690,
+    5562695,
+    5562699,
+    5562702,
+    5562707
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24eb50748d1e147fadd2d65a704137d605e3b1933a0b97b848d4ddb5a6242bfa
+oid sha256:a09c6084ebcadf937978efd342e6050168c4b6c2c653c5da5e93edc5d8df9cfa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8088975cf5fa272c1c9b575f839a87453089204b6979c668ab05e6f3d9a92ca
+oid sha256:eebfcd81ae0183214b76a387012f3f371b5c17630ad3fe59ce654bf40949699f
 size 4040701744