Run 4. Outer Step 65. Inner Step 89.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650752,
-    5650785
+    5650820,
+    5650855
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 87,
+  "inner_step": 89,
   "inner_steps": 0,
   "last_allreduce_block": 5648011,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc2c62be89749a84331154a34a457c0471fc940332cd8c4e5b2fd98d2314485e
+oid sha256:8bc3bf36649f18658255465bb42256d45a16774797a11bc56fcc420106682689
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5a34d7bcd5ea6cd320d83f5b93bf74dc1104402197c00b6e3578e4b7e3bea9
+oid sha256:b7b94099426d7d3a27366fd3b2fa12a87d5801eade68c3b3306892b19f00957b
 size 4040701744