Run 4. Outer Step 57. Inner Step 35.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5585792,
-    5585796,
-    5585800,
-    5585804,
-    5585808,
-    5585812
+    5585816,
+    5585820,
+    5585824,
+    5585828,
+    5585832
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10b1c645b182fc5bbd34813613e2fbaec5888885d2cb9edf23469699ac7da12
+oid sha256:b62b459aa978e9129a0feff3e49b96ccc37e342a9bc4da59d1815a2e4bc719c5
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c3c140d02a38d6eb69f64a68c789ccf8d3e5f8515e0ec995277415c8962478
+oid sha256:d6f520f56db126af98ce9179da9d05f1285c22391540de2a5d50c6a03a05519c
 size 4040701744