Run 4. Outer Step 54. Inner Step 89.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580228,
-    5580230,
-    5580233,
-    5580236,
-    5580238,
-    5580240,
-    5580242
+    5580245,
+    5580247,
+    5580250,
+    5580252,
+    5580254
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 88,
+  "inner_step": 89,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4bd38a533f035d9e973a5c06bd85f889e99e7bfb3439e59ca7c5622909df2e
+oid sha256:9d76942862d021fe55aa22b0e76b3f32fae3084775c7f88e56559129ceb8151e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe1c5eecaef599d95a7a5f8825c1bfe4099fddb81ac3cc6a18d1a6a701224b7
+oid sha256:076e6d3a58d255d5ffbfa0c820c826ae9963a7caaeef456a19eef514ed9faae7
 size 4040701744