Run 4. Outer Step 52. Inner Step 29.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575874,
-    5575876,
-    5575879,
-    5575882,
-    5575884,
-    5575886,
-    5575890
+    5575893,
+    5575895,
+    5575898,
+    5575900,
+    5575904
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01ece20fd4b4d2bcf807ba2e7d8d62fac8fdd08886d705e62b754c577ad6015b
+oid sha256:379f0900a9b224cff3a360d61c577b7cec15b54d9714b7ec612a1b9edd17cdd0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91109275a84a435059553ea91820e8988c99363cea6f7bdd5748e1b90615d3f9
+oid sha256:41cb3ac4ef9084099c697001e520ae7897b0f4392f8c3bf73381ebf6537f5a19
 size 4040701744