Run 4. Outer Step 3. Inner Step 137.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484813,
-    5484815,
-    5484818,
-    5484821,
-    5484825,
-    5484827,
-    5484829,
-    5484831,
-    5484833,
-    5484836
+    5484839,
+    5484842,
+    5484844,
+    5484849,
+    5484851
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 136,
+  "inner_step": 137,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4e573dbd65a5f67818bf3ca5e51ee42a798210a898636f3b4b2d2570c8304ae
+oid sha256:f1a63b20d44c6dfb670170189d5c71099c70f4a6699741715a1db6d7da249282
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c35dbc44d39c0e5ddee112eca63c83bf79cccbc101a47ce2a7eb9b9fda11b04f
+oid sha256:b12ec10fdde313309a9c297e0388cd2d0283db9e396e58165f4f3f664cfbf39f
 size 4040701744