Run 4. Outer Step 59. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5606902,
-    5606906,
-    5606911,
-    5606915,
-    5606920
+    5606925,
+    5606929,
+    5606934,
+    5606938,
+    5606943
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb0b2951d2a9be292f914063a46a46840c67b64f093c56aaa8e9f98eb71c773
+oid sha256:b8b2fbe71cae66113f4d2103900f7601f722888716f7e5e85961e6604efbce0f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec47e642ff5c228c8b0eb473c6cb6295b1c7d41cce25bbf9cda63947e2be511
+oid sha256:405f9e82d82c8a19b55145b90944cbf946be4eaca477aa49e3f66ebcb7566224
 size 4040701744