Run 4. Outer Step 64. Inner Step 163.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5615642,
-    5615647,
-    5615650,
-    5615655,
-    5615659
+    5615663,
+    5615667,
+    5615671,
+    5615675,
+    5615680
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 162,
+  "inner_step": 163,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d618563dcd5202907af9102a320aacb02390995b3e57258447e8c2f90f1f55
+oid sha256:07494e764896aafefffd4e3deee0740cd797177b8425dec61196cfdd72799503
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba735ed133315c18bb73376b736a5d72189d994a27cbe72650601434ae28f8c
+oid sha256:0dc9d87e86ec4650d099e35539a701666ac93c6a0679f0fa22365e12ac4cda1a
 size 4040701744