Run 3. Outer Step 9. Inner Step 56.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5400265,
-    5400268,
-    5400271,
-    5400274,
-    5400277
+    5400304,
+    5400307,
+    5400314,
+    5400317,
+    5400320
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a952a977a1d195ac37a23447e4c35367a0dc320782d4797a39d785b607d645
+oid sha256:d28d25f863888f972f332059d8ebebcfa76a6e889059465c49b803b7b8eabfa1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4acb7ff8ef4683416b90f25d37bd0b495b8a0e29faad15fa15b59ab59ee08f6
+oid sha256:7060029d747b08033be6af224b0f716704ce71c9d9b755e37c1dcc0c0c67751f
 size 4040701744