Run 4. Outer Step 50. Inner Step 150.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5625019,
-    5625051
+    5625084,
+    5625115
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 148,
+  "inner_step": 150,
   "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 sha256:5b8e5b547109b376866269047719166ecc4c936b9cc8a12272264bd7b0a9ba70
+oid sha256:2cd5f7f9eaa21113356ee16f7193171af3c46189ed185d99b7bac6c34999ded9
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9aa2fcdc2a17cae8aac23d8645068023829222f01516f29d2ccebb797a0351
+oid sha256:e3ca98c97392ef396395fa1e4976d78b91d20caaeac16320d85316bcdce4dbe3
 size 4040701744