Run 4. Outer Step 40. Inner Step 43.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556391,
-    5556394,
-    5556396,
-    5556398,
-    5556401,
-    5556404,
-    5556406
+    5556409,
+    5556411,
+    5556412,
+    5556414,
+    5556415
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a29673c91d96255f32534049f6a169ca5fdcf5216450b7957b784b30c7d85a8
+oid sha256:5c05be0926409e0d50861253f432f635544b02550a726eaa8bc817e2b31aaeb3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49fea3ed4c96c564e9a6910bf5b89a6240b816282d3f2afe4353a37bf977dfa
+oid sha256:dadbc9e538b2c3266d9e32539d0e8a71536a3c19ccf46745577b2c1921df6bcc
 size 4040701744