Run 4. Outer Step 58. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602903,
-    5602910,
-    5602917,
-    5602923,
-    5602930
+    5602938,
+    5602946,
+    5602953,
+    5602960,
+    5602967
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4fd2d7812dddd0ab26c5b1dbc2c9e76fe0d336e5a45f0e5026d7c6765606eb7
+oid sha256:9e1333da74585253871807bca1b0bb49c5760502657f6e83bab9da466da9dc41
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3662e0f86ebc9e20fd32566084b915e1325862b0ec942da7830f6eda416945ea
+oid sha256:91f98fd599372ef5a26b9179a58861c16ec95bea40ee28fdb8759c4527edb5d6
 size 4040701744