Run 4. Outer Step 53. Inner Step 84.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588918,
-    5588922,
-    5588926,
-    5588930,
-    5588934,
-    5588938
+    5588942,
+    5588947,
+    5588951,
+    5588955,
+    5588958,
+    5588962
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 83,
+  "inner_step": 84,
   "inner_steps": 0,
   "last_allreduce_block": 5565072,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e965fd16882d3579b488b22fe57dd5814f4b55516aefd38b3c24a161ce3d1263
+oid sha256:58114c9018291eb93e2d4b6042957b2be322febd417569bc00dea5dd9178b971
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7caa68e0a49404a29d18eb30de53aa67d0d214d6e425aff183a8b5eef75914e
+oid sha256:71e3f6d0059bcc88a520a9c7e3eae719da096fda63ea5c2097e3d34ca7bdd4e2
 size 4040701744