Run 4. Outer Step 50. Inner Step 40.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572713,
-    5572717,
-    5572722,
-    5572726,
-    5572730
+    5572734,
+    5572738,
+    5572743,
+    5572747,
+    5572752,
+    5572756
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f8a03c508d26d696b0c722574b5876518a608fdcdb20e26cb4c0a2150bf471
+oid sha256:c4a1933edb9d51f2112bef3b72377612232bdd25b33d3644c1d52067a90be639
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12228731187e8cfb2eb3d1d91b5e702166e87ec59b2a80f317fd0f477909991b
+oid sha256:eff403d1d96942f2de934168c081d1828f60b14306b08bbcb259e510a263020a
 size 4040701744