Run 4. Outer Step 64. Inner Step 174.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5615967,
-    5615972,
-    5615977,
-    5615981,
-    5615985
+    5615991,
+    5615996,
+    5616001,
+    5616005,
+    5616010
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 173,
+  "inner_step": 174,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8155e13c3aea3ec1214fd3a1912c581842ad78e194f8d0bee3edea0418a898f7
+oid sha256:6cfcfb6c340782aa6e8de317560df3e0a7e851b04ca423865eddc53623ff2fa5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d757e34caed3cf37b9326cb82aa2ee373b08cab8ff00d2fc6b3c1f2cb52b241a
+oid sha256:2441630d97c788ad9e5e888ab1a70577e5dbe3971e40147b4549ae3678684d93
 size 4040701744