Run 4. Outer Step 54. Inner Step 82.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580019,
-    5580021,
-    5580023,
-    5580026,
-    5580028,
-    5580031,
-    5580033
+    5580037,
+    5580040,
+    5580041,
+    5580045,
+    5580047
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 81,
+  "inner_step": 82,
   "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 sha256:21fceb5c28b88a5b17eed8e21461e63dd1be714fcdadecf596cd6f35aaa4310b
+oid sha256:9a2ebf642d2062ce20d92e74abfe89e0632da0fbc0b12ab5af74e159d44a3174
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d6c4926ddd9d8f394ac1fc9b1f67004078aee5fcb0891a46e4888c88175de5
+oid sha256:a8d6bd115a4483d5cfbd87722be216d3630efd5e58f3ea29dc93fc4e01296e47
 size 4040701744