Outer Step 0. Inner Step 25. Batch Size 316

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5129881,
-    5129886,
-    5129894,
-    5129909,
-    5129916
+    5129933,
+    5129948,
+    5129957,
+    5129963,
+    5129975
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81ff3cc0846cb9edd08a2d70fb6ac64a38a6874aa064f03e411bdbeb16eb067
+oid sha256:6be04d082a703294062f7ab85901ab5616d73f0a63fdd2af31bc0ee0d26bed38
 size 4040701744