Run 4. Outer Step 60. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607808,
-    5607813,
-    5607817,
-    5607821,
-    5607826
+    5607832,
+    5607836,
+    5607841,
+    5607845,
+    5607849
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe76bff6f1483af209afc0162b8ac849abad01f8a56c4052e54af129e108aa7d
+oid sha256:b2cfc348477863c3e43db0b8a56dc20a92fd9d9fecd685fc2468096a7bd828ba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7d7c08943d157b713df243c5fd4a8904d576a44e933d6323b7709889e64a8b
+oid sha256:358bb49218ce2df0370001cf09022d6ac9174eaa79ecdb54b0f0a6939a823d19
 size 4040701744