Run 3. Outer Step 6. Inner Step 277.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5389577,
-    5389580,
-    5389584,
-    5389587,
-    5389591
+    5389618,
+    5389622,
+    5389625,
+    5389629,
+    5389632
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 274,
+  "inner_step": 276,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fdceeeb3a3baad5da4c594d691314fa847125046cebf9dbdf01aaad2000f632
+oid sha256:5a4cbeae5bd2cc721ca937831f4e9b3077a7adf03157fef8e4896e07cf7b6caa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfa1950a214fc53cd7712dd7bd613ae58b1a1dd5d2fe5220dc9d167a9d9cc18
+oid sha256:300fa911da505ebc17222a0a69c899f713986f883347484db129181b0e0fa16c
 size 4040701744