Run 4. Outer Step 36. Inner Step 42.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550782,
-    5550784,
-    5550787,
-    5550789,
-    5550791,
-    5550793,
-    5550796
+    5550799,
+    5550801,
+    5550803,
+    5550805,
+    5550807
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5773c6a4d8366aefe53eccd5d26c87d9b59d624d3ec665bac36b2ac705aeac7
+oid sha256:acf7e514d57574efeaf74f3825aea872d8287b7c377871d3d7a86e6fca5d2a26
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f3ee9726b4e687cd5ae629d980b6fa8ff78792f9f6d6e51d773d6a5695553e
+oid sha256:e93af86d41415e516c7885b26b4ff5ef1665309cbad1f18e45bb24661d57e777
 size 4040701744