Run 4. Outer Step 15. Inner Step 67.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514992,
-    5514996,
-    5514999,
-    5515003,
-    5515007,
-    5515010
+    5515014,
+    5515018,
+    5515022,
+    5515025,
+    5515029,
+    5515033
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 66,
+  "inner_step": 67,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e20779e7c453f30b1db8b691778475a57bf14f55b9f4d712bb51349412cf09
+oid sha256:97c326b32c2daef3e3aabde5021f11279640f5f4dac485849fb6b06c10656caa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784cb74a0458b531c798d886db211384f5daf3525f9924d0988a934e890ebd89
+oid sha256:7aa94a676949594b7dc3b1a966d37d0b6140b5b8901716f7464c3a1949d2b05f
 size 4040701744