Run 4. Outer Step 66. Inner Step 103.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5622010,
-    5622014,
-    5622018,
-    5622022,
-    5622026
+    5622031,
+    5622035,
+    5622039,
+    5622042,
+    5622046
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 102,
+  "inner_step": 103,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32320a0ee45898ffe7533944940e647ca0fcb933e44ed5722ee6bdf81f0edd25
+oid sha256:671d34b607528a4f2f179917e25095bc1e65e3d8926d95c90bf88266353abb80
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6881b49ba1d7ba62cce34ddd5f830c838a5d7960df267886f376205a085bb2
+oid sha256:a73aa7bb43a7033eeaa18289653cdd5aa4e17e3b6898b8a06b04dd7913d20031
 size 4040701744