Run 4. Outer Step 58. Inner Step 76.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604758,
-    5604762,
-    5604766,
-    5604770,
-    5604775
+    5604780,
+    5604784,
+    5604788,
+    5604792,
+    5604796
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 75,
+  "inner_step": 76,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b58f20364515637f518effc1be49cf414cab7b7b8fa6a849e9550c54feba526
+oid sha256:d6b493c7ae34bf1f882705f0d6fc63072ac33de8cabd915a73b007178924936b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:608a8a0bcd800ed6fb7096935a54ba5b6ce9239baf9a7dfb373a5ed420af989e
+oid sha256:ea1e807e4b37d61e7b0bb749adc2bd46641cc8acd26b6cc5e790f4483ef59123
 size 4040701744