Run 4. Outer Step 60. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607544,
-    5607548,
-    5607553,
-    5607557,
-    5607562
+    5607567,
+    5607571,
+    5607575,
+    5607581,
+    5607586
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "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 sha256:2ec3212067055a5bd18f3a12cd622eac2f7594ec34f7a2196199cf91a728ffe2
+oid sha256:9a483a67069d4aaf2647d288029290a80a6900d0f74f76a57627daea7ef8858e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5649f352d5597dab9dc8c9797f9cf90e3184d78a425bb8d974b3e4a25d4082ca
+oid sha256:554c10c67f7a7ef70dadbaebe7bc1b4284b28c819694132cc52aade3ac9ccf42
 size 4040701744