Run 4. Outer Step 54. Inner Step 83.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580049,
-    5580052,
-    5580054,
-    5580057,
-    5580058,
-    5580060,
-    5580061,
-    5580063,
-    5580066
+    5580069,
+    5580070,
+    5580074,
+    5580076,
+    5580078
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 83,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2ebf642d2062ce20d92e74abfe89e0632da0fbc0b12ab5af74e159d44a3174
+oid sha256:f715f5e5c288cef72782f0ac5086de58f9d6e52a4955cf4cac3cae46c21b901a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d6bd115a4483d5cfbd87722be216d3630efd5e58f3ea29dc93fc4e01296e47
+oid sha256:ddb6926c9e31ed24b4c22db8b521a6aeda5fab20d5320ed04021ba1415073eb8
 size 4040701744