Run 4. Outer Step 66. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5652194,
-    5652198,
-    5652203,
-    5652207,
-    5652211
+    5652216,
+    5652220,
+    5652224,
+    5652229,
+    5652233
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5651055,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91cc6d91c05153b5ad7b6bc5628803f985dc1103d556136032bbec1b0f82085d
+oid sha256:37728e6eb6961ea27997252379043aaa1121546ad79643d28c54cfed528e8503
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e30dee53a132f9c2f4439e41377068feeb9b01ab82c8d07baea244f340d06d
+oid sha256:ee2b847e430b41260eaf894c22689d1c50f816cf2695cfc280cb6b50a1e84d7b
 size 4040701744