Run 4. Outer Step 58. Inner Step 55.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604073,
-    5604076,
-    5604078,
-    5604080,
-    5604083
+    5604085,
+    5604087,
+    5604089,
+    5604092,
+    5604094,
+    5604096,
+    5604099,
+    5604102
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 54,
+  "inner_step": 55,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b4c11d816df33d64f284a828690f2bd79fdcbae8695679f94db1ff946b3c35e
+oid sha256:18b00c30dfc0203c04619a8254b60dcdbafe8fa8df33285424a3feef9685d7ac
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6881403936e07d4b4d08cc45f80e066ca9bab03fcf6c4077676117d02552e7e
+oid sha256:e788d1c692e4813ef23530d14106a6480ce7b8e35c2aad631fab56dacddc55d2
 size 4040701744